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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6881
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that denote relative size or quantity

    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
    on
    -0.83
    an
    -0.74
    <em>
    -0.70
    DA
    -0.67
    in
    -0.67
    le
    -0.67
    del
    -0.67
    da
    -0.66
    my
    -0.66
    men
    -0.65
    POSITIVE LOGITS
     relatively
    1.41
    relatively
    1.38
     Relatively
    1.33
    EDEFAULT
    1.22
    ^(@)
    1.22
    ViewFeatures
    1.16
    addContainerGap
    1.13
     Мексичка
    1.10
    >\<^
    1.09
    _^
    1.07
    Activations Density 0.101%

    No Known Activations