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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3281
    Prev
    Next
    INDEX
    Explanations

    references to organizations and their operational details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.70
    GeoNames
    -0.65
    routeProvider
    -0.63
     jScrollPane
    -0.62
    IsMutable
    -0.60
    featureID
    -0.58
    Personensuche
    -0.56
    FailureListener
    -0.56
    SharedDtor
    -0.53
    LayoutConstraint
    -0.52
    POSITIVE LOGITS
     posts
    0.82
     mails
    0.75
     hands
    0.70
     don
    0.69
     signs
    0.67
     uploads
    0.67
     files
    0.66
     ships
    0.65
     stocks
    0.65
     rents
    0.65
    Activations Density 0.366%

    No Known Activations