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 - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3401
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to function calls and return statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SqlParameter
    -0.62
    icksburg
    -0.52
    UIControlState
    -0.52
     createContext
    -0.52
     defaultdict
    -0.52
    bitField
    -0.51
    étaire
    -0.49
     strconv
    -0.48
    ГЛА
    -0.48
    FailureListener
    -0.47
    POSITIVE LOGITS
    );}
    0.97
    ";}
    0.93
    ();}
    0.91
    ;}
    0.88
    ']}
    0.78
     })}
    0.76
    "]}
    0.76
    ;}
    
    0.74
    )}
    0.73
    ")}
    0.72
    Activations Density 0.102%

    No Known Activations