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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 6782
    Prev
    Next
    INDEX
    Explanations

    discussions of conflicts or challenges in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     đã
    -0.86
     telah
    -0.80
    已
    -0.75
     récente
    -0.75
     récentes
    -0.71
    have
    -0.70
    recently
    -0.69
     consisted
    -0.69
     Recently
    -0.69
     recente
    -0.69
    POSITIVE LOGITS
     gets
    1.33
     becomes
    1.26
     goes
    1.23
     takes
    1.16
     begins
    1.12
     develops
    1.12
     makes
    1.11
     does
    1.08
     gives
    1.08
     starts
    1.07
    Activations Density 1.735%

    No Known Activations