© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2003
    Prev
    Next
    INDEX
    Explanations

    mentions of combinations or mixtures involving different elements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endwhile
    -0.78
    MLLoader
    -0.76
    ]--;
    -0.74
    apunov
    -0.74
    XMLSchema
    -0.73
    脚注の使い方
    -0.72
    nestjs
    -0.71
    Портал
    -0.71
    rometry
    -0.70
    resave
    -0.70
    POSITIVE LOGITS
     combination
    2.94
    combination
    2.75
     Combination
    2.71
    Combination
    2.65
     combinations
    2.58
     Combinations
    2.36
    combinations
    2.29
     combo
    2.21
     Kombination
    2.05
     combinaison
    1.93
    Activations Density 0.114%

    No Known Activations