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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 534
    Prev
    Next
    INDEX
    Explanations

    specific mathematical concepts and notations related to statistical modeling or data representation

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

    LaTeX math symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols and notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerStep
    -0.66
    DebuggerNonUser
    -0.55
    허
    -0.50
    JSP
    -0.48
    Números
    -0.48
    WebControls
    -0.48
     אנ
    -0.45
    reszcie
    -0.44
     ModelExpression
    -0.44
    }(-
    -0.44
    POSITIVE LOGITS
    AutoScale
    0.73
    zzleHttp
    0.70
    VolleyError
    0.61
    Scénario
    0.61
    UnsafeEnabled
    0.56
    verifyException
    0.56
    Geografia
    0.55
    \{\\
    0.54
    hatt
    0.53
     Categor
    0.53
    Activations Density 2.023%

    No Known Activations