© 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. 11110
    Prev
    Next
    INDEX
    Explanations

    references to specific application programming interfaces (APIs) and related components

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

    Abbreviations starting with "Ap" or "AP"

    np_acts-logits-general · gemini-2.0-flash

    "Ap" or "AP" prefixes to terms

    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
    contentLoaded
    -0.54
    MathML
    -0.49
    UrlResolution
    -0.44
    tvguidetime
    -0.44
     pouvoit
    -0.42
     eût
    -0.41
     Verhältnisse
    -0.40
     Stärke
    -0.39
     étoit
    -0.39
     pères
    -0.39
    POSITIVE LOGITS
     Ap
    0.84
     AP
    0.76
     ap
    0.71
    Ap
    0.65
     APR
    0.63
     Aps
    0.62
     Api
    0.59
    ap
    0.56
     Ape
    0.56
     aps
    0.55
    Activations Density 0.356%

    No Known Activations