© 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. 23-GEMMASCOPE-RES-16K
    6. 14700
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to algorithms and numerical methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DBNull
    -0.55
    migrationBuilder
    -0.49
     Vak
    -0.47
    réhen
    -0.47
    Vak
    -0.47
     Fulda
    -0.45
     tes
    -0.44
     StatelessWidget
    -0.44
     AppCompatTheme
    -0.43
    kheim
    -0.42
    POSITIVE LOGITS
     iterative
    0.96
     iterations
    0.95
     iteration
    0.93
     iter
    0.90
     iterate
    0.87
     convergence
    0.87
     Iterate
    0.80
     Iter
    0.80
     converges
    0.79
    iteration
    0.77
    Activations Density 1.137%

    No Known Activations