© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4236
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific concepts, particularly in genetics and biology

    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
    THISDAY
    -0.52
     више
    -0.52
    nö
    -0.51
    issance
    -0.48
    )++;
    -0.47
     Traveler
    -0.47
    anthrene
    -0.47
     ApiException
    -0.46
    τως
    -0.46
    throp
    -0.45
    POSITIVE LOGITS
     كومونز
    0.82
    mybatisplus
    0.72
     alcohol
    0.68
     Alcohol
    0.68
    minecraft
    0.67
    unknownFields
    0.65
     الاطلاع
    0.65
    encodeWith
    0.65
     CascadeType
    0.64
    alcohol
    0.63
    Activations Density 2.126%

    No Known Activations