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. 28406
    Prev
    Next
    INDEX
    Explanations

    specific references to T-shirts, particularly in relation to events or occasions

    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
    }));
    
    -0.85
    Portail
    -0.84
    numerusform
    -0.83
    }))
    
    -0.79
    ]),
    
    -0.76
    الحياه
    -0.73
    }),
    
    -0.72
    بسم
    -0.72
     ***!
    -0.71
    };*/
    -0.71
    POSITIVE LOGITS
    e
    0.72
    tų
    0.65
    S
    0.64
    E
    0.60
    O
    0.59
    P
    0.57
    K
    0.57
     stră
    0.57
    H
    0.57
    I
    0.56
    Activations Density 0.069%

    No Known Activations