© 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. 4-GEMMASCOPE-RES-16K
    6. 930
    Prev
    Next
    INDEX
    Explanations

    references to figures, charts, and statistical analyses in scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.69
     utafitiHapana
    -0.58
     Signalez
    -0.54
    ineno
    -0.46
     néz
    -0.44
    GenerationType
    -0.44
    hoga
    -0.43
    atother
    -0.42
    ună
    -0.42
    xiety
    -0.41
    POSITIVE LOGITS
    ViewChild
    0.75
    endphp
    0.70
     mineures
    0.66
     فريبيس
    0.65
     Waray
    0.62
    InjectAttribute
    0.60
    ̍
    0.59
     enrique
    0.58
     phụ
    0.55
     smaller
    0.54
    Activations Density 1.465%

    No Known Activations