© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 7705
    Prev
    Next
    INDEX
    Explanations

    references to specific documents, cases, or points related to legal or procedural matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    annica
    -0.54
    めでとう
    -0.52
    encodeWith
    -0.51
     pageContext
    -0.51
    mybatisplus
    -0.48
    roveň
    -0.45
    لينا
    -0.45
     calldata
    -0.45
    getcwd
    -0.45
    ArrowToggle
    -0.44
    POSITIVE LOGITS
     purposes
    2.67
     sake
    2.29
     purpose
    2.11
    purposes
    2.10
     Purposes
    1.92
    purpose
    1.67
     reasons
    1.61
    Purpose
    1.51
     Purpose
    1.47
     reason
    1.43
    Activations Density 0.475%

    No Known Activations