© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    6. 15625
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions and classifications in technical or medical contexts

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

    Follows symbols/characters like *, (, $, [, or numbers

    np_acts-logits-general · gemini-2.0-flash

    technical terms and configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mach
    -0.44
     lettore
    -0.37
    ...}
    -0.35
    ::_('
    -0.35
     referenties
    -0.35
     åren
    -0.35
     насељу
    -0.33
     judgement
    -0.33
     gulls
    -0.33
    соль
    -0.32
    POSITIVE LOGITS
    IUrlHelper
    0.51
    uxxxx
    0.50
    ViewImports
    0.50
    WireFormatLite
    0.49
    ValueStyle
    0.49
    providedIn
    0.48
    MigrationBuilder
    0.48
    styleType
    0.45
    elemField
    0.44
    enderror
    0.43
    Activations Density 1.348%

    No Known Activations