© 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. 25-GEMMASCOPE-RES-16K
    6. 12837
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong emotional reactions or moral judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.68
    ytick
    -0.66
    :+:
    -0.63
     فريبيس
    -0.61
    ChildScrollView
    -0.60
     onBind
    -0.55
    ProcessEvent
    -0.54
    Kontrola
    -0.53
     hư
    -0.53
    DrawerToggle
    -0.52
    POSITIVE LOGITS
     forth
    0.69
     measured
    0.66
     curt
    0.66
     comb
    0.61
     terse
    0.57
     tep
    0.56
     lukewarm
    0.56
     oblique
    0.56
     cordial
    0.53
     sard
    0.53
    Activations Density 0.499%

    No Known Activations