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. 57232
    Prev
    Next
    INDEX
    Explanations

    structured data and descriptions, particularly in XML-like 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
    '},
    
    -0.85
    )':
    -0.85
    })*/
    -0.77
     myſelf
    -0.72
    '));
    
    -0.72
    )*/
    -0.72
    '}),
    -0.71
    __':
    
    -0.71
    \<^
    -0.70
    ])))
    -0.70
    POSITIVE LOGITS
     onPostExecute
    0.51
     statement
    0.51
     remarks
    0.49
    관
    0.44
     statements
    0.44
    続きます
    0.43
     describe
    0.43
    readLine
    0.42
    ‍
    0.42
     state
    0.41
    Activations Density 0.012%

    No Known Activations