© 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. 27-GEMMASCOPE-RES-16K
    11. 10277
    Prev
    Next
    INDEX
    Explanations

    names of authors and their affiliations or contributions in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.54
     ویکی‌پدی
    -0.53
     Chwiliwch
    -0.52
     surla
    -0.51
    Transkript
    -0.51
     esternos
    -0.50
    HXLINE
    -0.50
    yntaxException
    -0.49
    setVerticalGroup
    -0.49
    MigrationBuilder
    -0.49
    POSITIVE LOGITS
     eds
    0.55
    ScopeManager
    0.52
     BytesLike
    0.42
    Hrsg
    0.42
     authors
    0.41
     Eds
    0.41
     contributors
    0.40
    Compiled
    0.38
    .
    0.38
     editors
    0.37
    Activations Density 0.233%

    No Known Activations