© 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. 13028
    Prev
    Next
    INDEX
    Explanations

    conditional statements and logical expressions in mathematical contexts

    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
    migrationBuilder
    -0.86
    PerformLayout
    -0.78
     ControllerBase
    -0.75
    '));
    -0.75
    '):
    -0.74
    principalTable
    -0.71
    /")
    -0.68
    .')
    -0.68
     ComVisible
    -0.66
    />";
    -0.66
    POSITIVE LOGITS
    else
    0.79
     otherwise
    0.74
     Otherwise
    0.72
    Otherwise
    0.71
    otherwise
    0.62
     else
    0.62
    否则
    0.58
     circonstances
    0.56
     jinak
    0.55
    そうで
    0.55
    Activations Density 0.337%

    No Known Activations