© 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. 24-GEMMASCOPE-RES-16K
    11. 14417
    Prev
    Next
    INDEX
    Explanations

    code-related syntax or structures, particularly those associated with programming logic or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets ending in closing curly braces

    np_acts-logits-general · gemini-2.0-flash

    closing brace or error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.62
    ArgsConstructor
    -0.61
     للاسماء
    -0.58
     AttributeSet
    -0.55
     referrerpolicy
    -0.55
    AndEndTag
    -0.54
     kasarigan
    -0.53
    ContentAlignment
    -0.51
     JUGA
    -0.48
    ølge
    -0.48
    POSITIVE LOGITS
     }
    0.79
    }//
    0.72
    }
    0.71
    //}
    0.70
    endmodule
    0.70
     end
    0.64
    ;}
    0.59
    ();}
    0.59
    getKeyCode
    0.59
     \}
    0.58
    Activations Density 0.214%

    No Known Activations