© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6165
    Prev
    Next
    INDEX
    Explanations

    references to secrecy and concealment in interpersonal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    discussion of secrets, hidden information, or concealment.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    expressions about secrecy or concealment, including hiding information or asking others not to disclose something.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    phrases related to concealing, hiding, or keeping information secret from others.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.61
    VersionUID
    -0.50
    enumii
    -0.50
     Geschmack
    -0.48
     taste
    -0.48
    ReusableCell
    -0.46
     alar
    -0.45
     PLWABN
    -0.45
    SourceChecksum
    -0.44
    TagHelper
    -0.44
    POSITIVE LOGITS
     hiding
    0.64
     concealment
    0.64
    Hiding
    0.62
    hiding
    0.58
     conceal
    0.58
     ukry
    0.56
     concealing
    0.56
     hides
    0.56
     concealed
    0.56
     hide
    0.55
    Activations Density 0.186%

    No Known Activations