© 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. 17-GEMMASCOPE-RES-16K
    6. 5503
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values and potential headers or sections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vatel
    -0.65
     Тол
    -0.62
     noqa
    -0.62
     Zufall
    -0.61
    di
    -0.60
    一个
    -0.60
    ża
    -0.60
    ces
    -0.59
    forma
    -0.58
    istic
    -0.58
    POSITIVE LOGITS
    9
    1.33
     NINE
    1.04
    nine
    1.01
    jestic
    0.93
     Phry
    0.92
    ۹
    0.91
     MSR
    0.90
     nueve
    0.88
    ninth
    0.87
     ninety
    0.86
    Activations Density 0.795%

    No Known Activations