© 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. 14-GEMMASCOPE-RES-16K
    6. 4393
    Prev
    Next
    INDEX
    Explanations

    elements related to data processing and database queries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.89
    rungsseite
    -0.66
    tagext
    -0.63
    }();
    -0.63
    LookAnd
    -0.62
    getJSONArray
    -0.60
    setVerticalGroup
    -0.60
    الحياه
    -0.58
    RegressionTest
    -0.58
     ModelExpression
    -0.56
    POSITIVE LOGITS
    oznam
    0.46
    escent
    0.45
    gonz
    0.45
     HttpNotFound
    0.44
     Shipped
    0.43
     TAK
    0.42
    ৎ
    0.41
    onOptions
    0.41
     Escu
    0.40
    idine
    0.40
    Activations Density 0.263%

    No Known Activations