© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 13624
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and web protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.55
    ?
    -0.55
    </h1>
    -0.47
     ?
    -0.46
    </h2>
    -0.46
     /*
    -0.44
    /**
    -0.42
     besides
    -0.42
     where
    -0.42
    ,
    -0.42
    POSITIVE LOGITS
    脚注の使い方
    1.01
     تضيفلها
    0.95
    ⓧ
    0.91
    تقاوى
    0.91
    tagHelperRunner
    0.88
    帖最后由
    0.87
    évaluateur
    0.86
     ModelExpression
    0.84
    ariConfig
    0.81
    RenderAtEndOf
    0.80
    Activations Density 0.108%

    No Known Activations