© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11295
    Prev
    Next
    INDEX
    Explanations

    key identifiers and classifications related to specific categories and events

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

    Tokens followed by specific punctuation or grammatical constructs

    np_acts-logits-general · gemini-2.0-flash

    GoldenWave substitutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.48
    دانشنامهٔ
    -0.36
     Если
    -0.30
    AutoScaleMode
    -0.27
     اگر
    -0.27
     pres
    -0.27
     penet
    -0.25
    mares
    -0.25
    ⇧
    -0.25
     де
    -0.24
    POSITIVE LOGITS
     Infór
    0.96
    pulseira
    0.82
    tênis
    0.76
    الدراسه
    0.76
     anún
    0.76
     geladeira
    0.76
    sofá
    0.73
    VYMaps
    0.72
     EconPapers
    0.71
     ब्रेकडाउन
    0.69
    Activations Density 1.279%

    No Known Activations