© 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. 5-GEMMASCOPE-RES-16K
    11. 8799
    Prev
    Next
    INDEX
    Explanations

    terms related to legislative or regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.89
    UnsafeEnabled
    -0.82
    parsedMessage
    -0.77
    contentLoaded
    -0.76
    principalTable
    -0.69
    }}$.
    -0.69
     дописавши
    -0.68
    PerformLayout
    -0.67
    
    -0.66
    Autoritní
    -0.66
    POSITIVE LOGITS
    ArgsConstructor
    0.82
    HasAnnotation
    0.69
    Hochspringen
    0.67
    databind
    0.60
    Referències
    0.57
     zwar
    0.57
     disponibilités
    0.57
    していますが
    0.55
    +#+
    0.54
     Akismet
    0.52
    Activations Density 3.438%

    No Known Activations