© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1354
    Prev
    Next
    INDEX
    Explanations

    links and references to external content

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

    URLs

    np_acts-logits-general · gemini-2.0-flash

    http and https URLs

    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
    DeleteBehavior
    -0.82
    '},
    -0.79
     disambiguazione
    -0.70
    Demografía
    -0.67
    loài
    -0.66
    MigrationBuilder
    -0.66
    AlterField
    -0.65
    mybatisplus
    -0.65
    createCanvas
    -0.63
     ujednoznacz
    -0.62
    POSITIVE LOGITS
     https
    3.07
     http
    3.04
    https
    2.90
    http
    2.88
     www
    2.10
    ttps
    1.85
    www
    1.79
    Https
    1.49
    ttp
    1.31
     Http
    1.28
    Activations Density 0.863%

    No Known Activations