© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12530
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and data formats

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

    Hexadecimal code snippets

    np_acts-logits-general · gemini-2.0-flash

    programming identifiers and hex codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.82
    AddTagHelper
    -0.73
     Савезне
    -0.72
     InputDecoration
    -0.70
     Administrativna
    -0.69
    InjectAttribute
    -0.68
     تضيفلها
    -0.67
    interopRequire
    -0.66
     autorytatywna
    -0.65
     nahilalakip
    -0.65
    POSITIVE LOGITS
    IntoConstraints
    0.36
    fromLTRB
    0.30
     oferty
    0.30
    thousands
    0.29
    ::_('
    0.29
     thousands
    0.28
     cirka
    0.28
    khidmatan
    0.28
     catalogo
    0.28
     Europy
    0.28
    Activations Density 1.570%

    No Known Activations