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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 15403
    Prev
    Next
    INDEX
    Explanations

    punctuation and delimiters used in code or structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noDo
    -0.48
    bar
    -0.46
    orial
    -0.43
    getExternal
    -0.42
    bart
    -0.40
    oc
    -0.40
     Außen
    -0.40
    FT
    -0.39
     vocês
    -0.39
    EXT
    -0.39
    POSITIVE LOGITS
    </caption>
    0.92
    ')));
    0.91
    }>;
    0.91
    "]);
    0.91
    "])
    
    0.90
    ]));
    
    0.89
    PreferredItem
    0.88
    ()];
    0.88
    ()]);
    0.87
    ")));
    0.87
    Activations Density 0.027%

    No Known Activations