© 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. 8-GEMMASCOPE-RES-16K
    11. 5662
    Prev
    Next
    INDEX
    Explanations

    instances of authorized actions and decisions within a legal or governmental context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाएं
    -0.85
     nahilalakip
    -0.75
    URLException
    -0.66
     doInBackground
    -0.66
     unknownFields
    -0.63
     externi
    -0.63
    WillAppear
    -0.62
    hoeddwyd
    -0.61
    PerformLayout
    -0.59
    hdashline
    -0.59
    POSITIVE LOGITS
    insegna
    0.59
    CrossRef
    0.49
     me
    0.49
    くれました
    0.47
     мәкал
    0.47
    くれます
    0.46
    celi
    0.46
     suggested
    0.44
     us
    0.44
     Hivatalos
    0.44
    Activations Density 1.154%

    No Known Activations