© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 26
    Prev
    Next
    INDEX
    Explanations

    references to citations and mentions of missing information

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

    citation omitted or missing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.73
    :✨
    -0.70
    AddTagHelper
    -0.68
    KommentareTeilen
    -0.67
    RenderAtEndOf
    -0.65
    InitVars
    -0.62
    IContainer
    -0.62
    تفصیلات
    -0.62
    ChildScrollView
    -0.59
    المشاركات
    -0.59
    POSITIVE LOGITS
     unclear
    0.42
     laajenta
    0.38
     unre
    0.37
     citation
    0.36
     confirmed
    0.36
    URG
    0.35
    Referensi
    0.35
    <i>
    0.35
     unresolved
    0.34
    pagen
    0.34
    Activations Density 0.012%

    No Known Activations