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. 16-GEMMASCOPE-RES-16K
    6. 14812
    Prev
    Next
    INDEX
    Explanations

    sections of documentation or code comments that describe functions or methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Opening brackets or quotes in code

    np_acts-logits-general · gemini-2.0-flash

    Javascript code closing braces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alada
    -0.57
     rockers
    -0.55
     Nhưng
    -0.54
     saluti
    -0.52
    իր
    -0.52
     للمعارف
    -0.50
     Egger
    -0.50
     mouseClicked
    -0.50
    enguin
    -0.50
    onar
    -0.50
    POSITIVE LOGITS
    }`).
    0.78
    })()
    0.74
     """
    
    0.73
    };*/
    0.72
    }])
    0.72
    }")]
    0.71
    }))
    
    0.69
    ])))
    0.68
    })).
    0.68
     raiſ
    0.68
    Activations Density 0.196%

    No Known Activations