© 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. 23-GEMMASCOPE-RES-16K
    11. 12645
    Prev
    Next
    INDEX
    Explanations

    references to methods and figures in academic documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -1.40
    enumi
    -0.73
    IntoConstraints
    -0.72
     متعلقه
    -0.63
    expandindo
    -0.61
    enumii
    -0.60
    thâu
    -0.59
     JpaRepository
    -0.59
     AttributeSet
    -0.57
     utafitiHapana
    -0.56
    POSITIVE LOGITS
     S
    3.22
     s
    2.72
    S
    2.62
     getS
    1.81
    getS
    1.76
     س
    1.61
    s
    1.53
    Ｓ
    1.46
    ｓ
    1.16
     С
    1.14
    Activations Density 0.901%

    No Known Activations