Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12560
    Prev
    Next
    INDEX
    Explanations

    terms related to the assessment of potential and risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adaptiveStyles
    -0.60
     capace
    -0.59
    ViewImports
    -0.57
     myſelf
    -0.55
     withal
    -0.51
     Jefus
    -0.51
     occurred
    -0.49
     esternos
    -0.49
     poffe
    -0.48
     themſelves
    -0.48
    POSITIVE LOGITS
     intact
    0.78
    tvguidetime
    0.77
     limited
    0.77
     varied
    0.74
     minimal
    0.74
     plentiful
    0.73
     impeccable
    0.73
     diverse
    0.69
     compromised
    0.68
     enhanced
    0.68
    Activations Density 0.872%

    No Known Activations