© 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. 15-GEMMASCOPE-RES-16K
    11. 8307
    Prev
    Next
    INDEX
    Explanations

    programming and data structure related iterations and data manipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -1.05
     BoxFit
    -1.00
    IndentedString
    -0.98
    CloseOperation
    -0.95
    LookAnd
    -0.93
    tagHelperRunner
    -0.92
    IVEREF
    -0.89
    fjspx
    -0.89
     Мексичка
    -0.87
    localctx
    -0.82
    POSITIVE LOGITS
    .
    0.53
    ↵
    0.49
     hänen
    0.41
    roveň
    0.40
    )
    0.40
     sjø
    0.39
     judiciales
    0.39
     disparu
    0.38
     seva
    0.38
     tamam
    0.38
    Activations Density 0.181%

    No Known Activations