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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 9020
    Prev
    Next
    INDEX
    Explanations

    academic journal references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers in square brackets

    np_acts-logits-general · gemini-2.0-flash

    journal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gameserver
    -0.61
     ModelExpression
    -0.57
    InjectAttribute
    -0.56
     prochaines
    -0.55
    DMSO
    -0.55
    cellor
    -0.54
     négociations
    -0.52
     prisonniers
    -0.52
     juger
    -0.52
     Prisoner
    -0.52
    POSITIVE LOGITS
    Tazama
    0.61
    ufnahme
    0.52
    <?
    0.51
    ATORY
    0.49
    zeki
    0.48
    ByPrimaryKey
    0.47
    ificent
    0.45
    isseau
    0.45
    存于互联网档案馆
    0.44
    ientí
    0.44
    Activations Density 0.152%

    No Known Activations