© 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. 2904
    Prev
    Next
    INDEX
    Explanations

    verbs indicating actions related to change or influence

    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
    .
    -0.61
     
    -0.51
    ↵↵
    -0.46
    -
    -0.45
    <eos>
    -0.45
     (
    -0.44
    gen
    -0.44
     fatica
    -0.43
     -
    -0.42
    ,
    -0.42
    POSITIVE LOGITS
     itſelf
    0.97
    ]--;
    0.92
    帖最后由
    0.90
     Monfieur
    0.88
     ―――――
    0.87
     kaarangay
    0.85
    TagMode
    0.85
     Reverso
    0.84
     Shakspeare
    0.84
     StatelessWidget
    0.83
    Activations Density 0.515%

    No Known Activations