© 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. 6115
    Prev
    Next
    INDEX
    Explanations

    coding or programming-related syntax elements and keywords

    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
    T
    -1.30
     t
    -1.21
     T
    -1.19
    t
    -1.04
    ｔ
    -0.94
    𝘁
    -0.94
    ᴛ
    -0.91
    getT
    -0.87
    Ｔ
    -0.86
    𝐭
    -0.85
    POSITIVE LOGITS
    uxxxx
    0.52
    Portale
    0.49
    دانشنامهٔ
    0.49
    المناصب
    0.45
    migrationBuilder
    0.44
    UnknownFieldSet
    0.41
    ftagPool
    0.41
     LUMP
    0.40
     unknownFields
    0.40
     دیکھیے
    0.40
    Activations Density 1.052%

    No Known Activations