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. 10-GEMMASCOPE-RES-16K
    6. 3108
    Prev
    Next
    INDEX
    Explanations

    technical terms and data structures related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     P
    -0.52
    td
    -0.52
    P
    -0.52
    sel
    -0.50
    ".$_
    -0.49
     M
    -0.49
    E
    -0.48
    M
    -0.47
    cella
    -0.47
    cel
    -0.46
    POSITIVE LOGITS
    Geplaatst
    1.18
    SharedCtor
    1.08
    CloseOperation
    1.01
    protoimpl
    1.01
    LabelTagHelper
    1.00
    nologue
    0.99
    ArgsConstructor
    0.94
    VersionUID
    0.92
     يتيمه
    0.91
    TintMode
    0.91
    Activations Density 1.054%

    No Known Activations