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. 4-GEMMASCOPE-RES-16K
    6. 16007
    Prev
    Next
    INDEX
    Explanations

    structured data types and programming constructs

    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
     _
    -0.50
    ostic
    -0.46
    二是
    -0.43
    ubwa
    -0.42
     chain
    -0.42
     península
    -0.42
    Params
    -0.42
    InSection
    -0.42
     <
    -0.42
    不解
    -0.42
    POSITIVE LOGITS
    parsedMessage
    1.05
    aarrggbb
    0.87
    GEBURTSDATUM
    0.84
    IUrlHelper
    0.84
    titleMargin
    0.81
    simpleType
    0.79
    VersionUID
    0.78
    bewerken
    0.78
    uxxxx
    0.78
    ագրություններ
    0.78
    Activations Density 0.910%

    No Known Activations