© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1998
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of places, organizations, and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymce
    -0.86
    Diwedd
    -0.79
    modelBuilder
    -0.70
     الرخصة
    -0.64
    lapsing
    -0.64
    LookAnd
    -0.58
    ghijklmnop
    -0.58
    jeuner
    -0.57
     Milling
    -0.57
     Irrit
    -0.57
    POSITIVE LOGITS
     will
    0.62
     was
    0.58
     records
    0.58
     Ouverture
    0.56
    脚注の使い方
    0.55
     services
    0.53
     has
    0.52
    bability
    0.52
    StructEnd
    0.52
    ,
    0.51
    Activations Density 0.221%

    No Known Activations