© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11376
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to programming and function definitions

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

    Code, often related to variable assignments or debugging

    np_acts-logits-general · gemini-2.0-flash

    conditional code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     return
    -0.71
    NewUrlParser
    -0.71
    Returning
    -0.69
    ScopeManager
    -0.69
    IVEREF
    -0.68
    returning
    -0.68
     StatelessWidget
    -0.67
    yntaxException
    -0.67
    脚注の使い方
    -0.66
    
    -0.66
    POSITIVE LOGITS
    bitField
    0.51
    goto
    0.49
    ↵↵
    0.49
    *);
    0.46
    })();
    
    0.45
    DebuggerStep
    0.42
    ),),
    0.41
    )?;
    0.40
     @"/
    0.40
    ();
    0.40
    Activations Density 0.057%

    No Known Activations