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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 7608
    Prev
    Next
    INDEX
    Explanations

    evidence of children's behavior and testimonies regarding aggression and observation

    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
     utafitiHapana
    -0.67
    StoryboardSegue
    -0.65
     AttributeSet
    -0.60
    -------
    -0.60
    scriptId
    -0.59
     referenties
    -0.59
    تقاوى
    -0.57
     متعلقه
    -0.56
    脚注の使い方
    -0.55
    ichord
    -0.54
    POSITIVE LOGITS
     seeing
    2.57
     sees
    2.35
     see
    2.30
     saw
    2.30
    seeing
    2.15
     seen
    2.14
     Seeing
    2.06
    Seeing
    2.03
     witnessing
    1.94
    see
    1.89
    Activations Density 0.649%

    No Known Activations