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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 702
    Prev
    Next
    INDEX
    Explanations

    terminology and concepts related to technology and its applications

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

    end of phrase or clause

    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
     فريبيس
    -0.47
     propOrder
    -0.43
    ScopeManager
    -0.42
     resourceCulture
    -0.38
    FormTagHelper
    -0.34
    []
    -0.33
    saraba
    -0.33
    المكان
    -0.33
    RenderAtEndOf
    -0.32
    UnusedPrivate
    -0.32
    POSITIVE LOGITS
     kasarigan
    0.83
    хьтан
    0.60
    Dislikes
    0.48
    󠁴
    0.46
     miniaturka
    0.46
    EnumMember
    0.46
    oplan
    0.46
    Msk
    0.46
    Concurrency
    0.45
    滯
    0.45
    Activations Density 0.158%

    No Known Activations