© 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. 9-GEMMASCOPE-RES-16K
    11. 10220
    Prev
    Next
    INDEX
    Explanations

    references to book or movie covers and related artwork

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

    Image representation: album covers and headers

    np_acts-logits-general · gemini-2.0-flash

    cover art and headers

    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
     CreateTagHelper
    -0.60
    новништво
    -0.54
    IUrlHelper
    -0.53
     createSlice
    -0.52
     Réponses
    -0.52
    يكب
    -0.48
    awtextra
    -0.45
    ніципалі
    -0.45
     pihaknya
    -0.44
    TokenNameDOT
    -0.44
    POSITIVE LOGITS
     cover
    1.13
    cover
    1.02
     Cover
    0.98
    Cover
    0.96
     COVER
    0.86
    COVER
    0.73
    封面
    0.72
     обло
    0.65
     封面
    0.64
     banner
    0.63
    Activations Density 0.162%

    No Known Activations