© 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 - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 540
    Prev
    Next
    INDEX
    Explanations

    terms and functions related to programming and data structures

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

    Code-related terms, often after punctuation

    np_acts-logits-general · gemini-2.0-flash

    technical keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     judiciales
    -0.21
     Künst
    -0.21
    seamnă
    -0.20
     mãos
    -0.19
     face
    -0.19
     senior
    -0.19
     tölt
    -0.19
     maș
    -0.18
     tried
    -0.18
     suje
    -0.18
    POSITIVE LOGITS
    Tikang
    0.75
    UnusedPrivate
    0.74
    OGND
    0.73
    mbgg
    0.71
     betweenstory
    0.69
    IUrlHelper
    0.69
    msgTypes
    0.68
     Houſe
    0.66
    postsleuth
    0.65
    ロウィン
    0.65
    Activations Density 0.990%

    No Known Activations