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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9971
    Prev
    Next
    INDEX
    Explanations

    terms related to insertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }]
    
    -0.64
    }],
    
    -0.63
    ]',
    -0.61
    pricht
    -0.61
    lihood
    -0.60
     estekak
    -0.59
    ]`
    -0.56
    )`
    -0.56
    `,
    
    -0.54
    ">//
    -0.54
    POSITIVE LOGITS
     noses
    0.90
     nose
    0.90
    nose
    0.78
     Nights
    0.77
     Mosque
    0.75
    Nose
    0.73
     Nose
    0.73
     nos
    0.73
    nos
    0.69
    nights
    0.69
    Activations Density 0.062%

    No Known Activations