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. 18-GEMMASCOPE-RES-16K
    6. 8601
    Prev
    Next
    INDEX
    Explanations

    terms related to biological transfer mechanisms and processes

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

    "transfer" and its variations

    np_acts-logits-general · gemini-2.0-flash

    Transfer RNA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.63
    time
    -0.63
    тино
    -0.59
    ння
    -0.58
    onAttach
    -0.57
    й
    -0.57
     CÁ
    -0.57
     Seri
    -0.56
    usc
    -0.56
    keit
    -0.55
    POSITIVE LOGITS
     HasFactory
    0.79
     newBuilder
    0.78
     ModelExpression
    0.78
    Transfers
    0.77
     transfers
    0.76
    ToServer
    0.75
    multer
    0.74
    లాలు
    0.74
     estekak
    0.73
    Décès
    0.73
    Activations Density 0.157%

    No Known Activations