Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2107
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to method definitions and parameters

    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
    __':
    
    -0.78
    __":
    
    -0.67
    ++
    
    -0.66
    gatsby
    -0.57
    期刊论文
    -0.51
    mediaPlayer
    -0.49
    =[]
    
    -0.49
    ={()=>
    -0.48
    \"]
    -0.48
    DockStyle
    -0.48
    POSITIVE LOGITS
    ;
    1.70
    ;
    1.47
    $;
    1.46
    ?;
    1.44
    »;
    1.44
    ';
    1.42
    ”;
    1.39
    ’;
    1.38
     "";
    1.37
    '';
    1.37
    Activations Density 0.550%

    No Known Activations