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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28488
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]');
    -0.57
    HasForeignKey
    -0.56
    intios
    -0.54
    "]);
    
    -0.50
     });
    
    -0.49
    )];
    
    -0.48
     "");
    
    -0.48
     alles
    -0.47
    ktop
    -0.46
     misc
    -0.46
    POSITIVE LOGITS
    ']=='
    0.73
    windowFixed
    0.72
     disambiguazione
    0.71
    =="
    0.68
    ]=="
    0.66
    =='
    0.66
    SPJ
    0.65
    culin
    0.63
    hasOwnProperty
    0.63
    ✨:
    0.63
    Activations Density 0.025%

    No Known Activations