Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6697
    Prev
    Next
    INDEX
    Explanations

    initial markers indicating the beginning of sections or distinct arguments within a text

    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
    WriteBarrier
    -0.91
    aarrggbb
    -0.91
    sizeCache
    -0.90
     &___
    -0.85
    IonicModule
    -0.81
    mergeFrom
    -0.78
    ModelSerializer
    -0.77
    WireFormatLite
    -0.77
    TypedDataSet
    -0.76
    GraphicsUnit
    -0.73
    POSITIVE LOGITS
    jupiter
    1.08
     goal
    0.60
    frist
    0.60
     roule
    0.58
    zwei
    0.56
     zakon
    0.55
    kurat
    0.54
    runner
    0.54
    רושלים
    0.54
     GOAL
    0.54
    Activations Density 0.004%

    No Known Activations