© 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. 7-GEMMASCOPE-RES-16K
    6. 8532
    Prev
    Next
    INDEX
    Explanations

    instances of method definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Steck
    -0.59
     pector
    -0.56
     apret
    -0.55
     maß
    -0.55
    TokenNameLBRACE
    -0.53
     Shee
    -0.53
     Elin
    -0.53
    siz
    -0.51
     immagin
    -0.51
     Ärz
    -0.51
    POSITIVE LOGITS
     void
    1.39
     /\.
    1.00
    void
    0.94
    Void
    0.91
    })).
    0.90
    "]').
    0.89
     VOID
    0.87
    enderror
    0.86
     voids
    0.84
     Void
    0.83
    Activations Density 0.011%

    No Known Activations