Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13907
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific formatting or data structure notations, such as braces and brackets

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

    Code delimiters or brackets

    np_acts-logits-general · gemini-2.0-flash

    cur or region

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didSet
    -0.64
     arşivlendi
    -0.60
     становника
    -0.54
    Diwedd
    -0.53
    AndEndTag
    -0.53
    хьтан
    -0.53
     strerror
    -0.52
    ⟬
    -0.52
     clf
    -0.51
    AutoScale
    -0.51
    POSITIVE LOGITS
    },{
    0.76
    })
    
    0.73
     ...
    0.68
    }),
    
    0.67
    },
    
    0.66
    ↵
    0.66
    }).
    0.66
    });
    
    0.64
     bers
    0.64
    }),
    0.63
    Activations Density 0.132%

    No Known Activations