© 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. 24-GEMMASCOPE-RES-16K
    11. 14532
    Prev
    Next
    INDEX
    Explanations

    terminology related to security and data integrity in communication systems

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

    starting with "fi", "fl", "speci", or "scienti"

    np_acts-logits-general · gemini-2.0-flash

    restrict configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </i>
    -2.19
    </b>
    -2.09
    <i>
    -1.77
    <b>
    -1.40
    <u>
    -1.11
    例文帳に追加
    -1.10
    ՚
    -0.92
    dfrac
    -0.89
    <sup>
    -0.85
    '></
    -0.82
    POSITIVE LOGITS
     fi
    1.45
     speci
    1.43
     first
    1.40
     fl
    1.38
     bene
    1.31
    fi
    1.24
     modi
    1.22
    fl
    1.20
     sign
    1.16
     scienti
    1.15
    Activations Density 1.261%

    No Known Activations