© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9698
    Prev
    Next
    INDEX
    Explanations

    structured numerical data and specific references to places, studies, or methodologies in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text within brackets

    np_acts-logits-general · gemini-2.0-flash

    citations and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -0.67
    wiſe
    -0.59
    \%)
    -0.59
    .",
    -0.59
    reszcie
    -0.59
    leſs
    -0.58
     }}$}
    -0.58
    iffion
    -0.58
    \%,
    -0.58
     fianco
    -0.57
    POSITIVE LOGITS
    aarrggbb
    0.80
    ThroughAttribute
    0.77
     متعلقه
    0.63
     defaultstate
    0.59
     &
    0.57
    Cyfeiriadau
    0.55
    principalColumn
    0.55
     interesar
    0.55
     {@
    0.54
    Przypisy
    0.54
    Activations Density 1.873%

    No Known Activations