© 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. 23-GEMMASCOPE-RES-16K
    6. 14736
    Prev
    Next
    INDEX
    Explanations

    elements related to legal reasoning and justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.65
     مشين
    -0.63
     StatefulWidget
    -0.60
     atque
    -0.59
     дописавши
    -0.57
    anyon
    -0.56
    erdings
    -0.55
     Brava
    -0.55
    enderror
    -0.54
    saraba
    -0.53
    POSITIVE LOGITS
     mainly
    2.55
     primarily
    2.45
     mostly
    2.38
     largely
    2.19
     chiefly
    2.12
     predominantly
    2.10
    primarily
    2.10
    mainly
    2.08
     principally
    2.08
     Mainly
    2.07
    Activations Density 0.588%

    No Known Activations