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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1102
    Prev
    Next
    INDEX
    Explanations

    terms related to investigation or searching for deeper truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases involving the pursuit of truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    going beneath the surface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     nakalista
    -0.94
    новниш
    -0.88
     resourceCulture
    -0.80
    MockMvc
    -0.79
    astify
    -0.78
     Италијани
    -0.76
     utafitiHapana
    -0.75
    PreferredItem
    -0.72
    oredCriteria
    -0.70
    featureID
    -0.69
    POSITIVE LOGITS
     underlying
    1.32
     deeper
    1.20
    underlying
    1.18
     Underlying
    1.14
     beneath
    1.11
     surface
    1.05
     Beneath
    1.02
    Underlying
    1.01
     underneath
    1.01
     root
    1.01
    Activations Density 0.195%

    No Known Activations