© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 516
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or system administration

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

    phrases describing things that are ahead of their time or anticipatory in nature.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     murale
    -0.38
     censiti
    -0.37
    EDEFAULT
    -0.36
    mios
    -0.34
    oneofs
    -0.33
     tarde
    -0.32
     late
    -0.32
    hyrchwyd
    -0.32
    Late
    -0.32
    Indirect
    -0.31
    POSITIVE LOGITS
     ahead
    2.44
     Ahead
    2.14
    ahead
    2.09
    Ahead
    2.00
     AHEAD
    1.91
     front
    1.84
     delante
    1.52
     Front
    1.50
    front
    1.48
     precede
    1.44
    Activations Density 0.443%

    No Known Activations