© 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. 1088
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or articles indicating significant topics or subjects in the document

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

    phrases related to official organizations and leadership roles.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     intensity
    -0.44
    licópter
    -0.42
    glBind
    -0.42
    xtext
    -0.40
    PYX
    -0.40
     sorpresas
    -0.40
    ൃ
    -0.40
    antwoorden
    -0.40
    ulgação
    -0.40
     الظ
    -0.39
    POSITIVE LOGITS
    Portale
    0.53
     the
    0.52
     Référence
    0.52
    ValueStyle
    0.50
     newly
    0.50
     Masyarakat
    0.49
    newly
    0.47
    󠁢
    0.45
    enumi
    0.44
    EndGlobalSection
    0.43
    Activations Density 0.404%

    No Known Activations