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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17-GEMMASCOPE-RES-16K
    6. 1200
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating certainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.74
    opsida
    -0.73
    CloseOperation
    -0.69
     alimentaires
    -0.68
     Jefus
    -0.64
     inoxid
    -0.60
     виправивши
    -0.60
    romeo
    -0.59
    orgung
    -0.58
     médicaux
    -0.58
    POSITIVE LOGITS
     be
    1.22
     also
    1.12
     not
    1.07
     have
    1.07
     never
    0.99
     always
    0.98
     actually
    0.98
     still
    0.91
     certainly
    0.90
     indeed
    0.89
    Activations Density 0.595%

    No Known Activations