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. 10-GEMMASCOPE-RES-16K
    6. 3154
    Prev
    Next
    INDEX
    Explanations

    tokens related to programming or markup language syntax, particularly those that govern content structure or flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }$​
    -0.71
    ">//
    -0.67
    $​
    -0.66
    __':
    -0.65
    >--}}
    -0.60
    __':
    
    -0.58
    ]}>
    -0.55
     AspNetCore
    -0.54
    tagHelperRunner
    -0.53
    )』
    -0.52
    POSITIVE LOGITS
    audiovisuel
    0.92
    Hrsg
    0.83
    NOPQRST
    0.79
     ​​
    0.74
     Rptr
    0.73
    cookieParser
    0.72
     ويكيميديا
    0.72
    randomUUID
    0.72
    Rptr
    0.71
    Secondly
    0.67
    Activations Density 1.234%

    No Known Activations