Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7294
    Prev
    Next
    INDEX
    Explanations

    punctuation and code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     становника
    -0.38
    EDEFAULT
    -0.38
    ɕ
    -0.38
    ArgsConstructor
    -0.31
     наступа
    -0.31
    ліст
    -0.30
    DataSnapshot
    -0.30
     gì
    -0.30
    oubliez
    -0.30
    ждый
    -0.30
    POSITIVE LOGITS
    AutoScaleMode
    0.73
    AutoScale
    0.60
    %");
    0.52
    RegressionTest
    0.51
    הערות
    0.51
    IContainer
    0.50
    PerformLayout
    0.48
    StoryboardSegue
    0.47
    %";
    0.47
    Controls
    0.47
    Activations Density 0.007%

    No Known Activations