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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 4037
    Prev
    Next
    INDEX
    Explanations

    references to mathematical functions, variables, and operations related to equations or formulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )++;
    -0.77
     positively
    -0.69
    }^{+}
    -0.63
    ^{+}
    -0.61
    ^+
    -0.60
    }_{+
    -0.58
     Positive
    -0.58
    _{+}
    -0.58
    ^{+}$
    -0.58
    _{+
    -0.58
    POSITIVE LOGITS
    NegativeButton
    0.89
     negative
    0.70
    ConstraintMaker
    0.68
     المعيارى
    0.68
     negatif
    0.66
    ReusableCell
    0.66
    negative
    0.64
    migrationBuilder
    0.64
     negativos
    0.63
    AccessorTable
    0.62
    Activations Density 0.740%

    No Known Activations