© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1697
    Prev
    Next
    INDEX
    Explanations

    technical terms related to biological components and materials

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

    preceding locations or parts within something

    np_acts-logits-general · gemini-2.0-flash

    inside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Polize
    -0.39
    IntoConstraints
    -0.36
     neutrality
    -0.35
     Sempre
    -0.35
    InjectAttribute
    -0.35
     politically
    -0.35
     compañeros
    -0.35
    styleUrls
    -0.33
     policeman
    -0.33
    udent
    -0.32
    POSITIVE LOGITS
     inside
    0.95
    inside
    0.89
     Inside
    0.82
    Inside
    0.82
    INSIDE
    0.79
     INSIDE
    0.79
     insides
    0.75
     interior
    0.75
    interior
    0.69
    intérieur
    0.65
    Activations Density 0.894%

    No Known Activations