© 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-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1374
    Prev
    Next
    INDEX
    Explanations

    information about project proposals and their benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.63
     étoit
    -0.57
    WireFormatLite
    -0.56
    makeConstraints
    -0.53
    brunnen
    -0.53
    enterOuterAlt
    -0.52
    oa̍t
    -0.52
     contextLoads
    -0.51
    figsize
    -0.50
     imageNamed
    -0.50
    POSITIVE LOGITS
     allows
    1.03
     Allows
    0.99
     avoids
    0.94
    Allows
    0.90
     allow
    0.85
     allowing
    0.81
     avoid
    0.81
    allows
    0.79
     Gives
    0.75
     Vorteil
    0.75
    Activations Density 0.617%

    No Known Activations