© 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. 10-GEMMASCOPE-RES-16K
    6. 12355
    Prev
    Next
    INDEX
    Explanations

    various roles and identities people hold in their personal and professional lives

    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
    httphttps
    -0.54
    lioz
    -0.53
    Filed
    -0.52
    jestic
    -0.52
    RuleContext
    -0.52
     hjælpe
    -0.51
    ecco
    -0.51
    seers
    -0.51
    WithFormat
    -0.50
    StoryboardSegue
    -0.50
    POSITIVE LOGITS
    PerformLayout
    0.82
    uxxxx
    0.76
    queryInterface
    0.67
    -------------</
    0.63
     дописавши
    0.60
     lenker
    0.60
     فريبيس
    0.57
    AutoScaleMode
    0.56
     utafitiHapana
    0.55
     ASR
    0.54
    Activations Density 0.423%

    No Known Activations