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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14721
    Prev
    Next
    INDEX
    Explanations

    technical details related to debugging and authentication processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.71
    ########.
    -0.70
     OFDb
    -0.64
    sizeCache
    -0.60
    rungsseite
    -0.59
    OGND
    -0.57
    Tikang
    -0.57
    #+#
    -0.55
     lenker
    -0.54
     adopción
    -0.54
    POSITIVE LOGITS
    GOTREF
    0.45
    httphttps
    0.42
    retty
    0.40
    verifyException
    0.40
     ...
    0.39
    uxxxx
    0.39
     Orange
    0.39
     nicely
    0.38
     normal
    0.38
     brand
    0.38
    Activations Density 1.693%

    No Known Activations