© 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. 3-GEMMASCOPE-RES-16K
    6. 2041
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses that initiate with "how to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.78
    Personensuche
    -0.74
    posedge
    -0.73
    
    -0.69
    setAccessible
    -0.68
     Manuf
    -0.66
     photolibrary
    -0.64
     unsplash
    -0.64
    ^(@)
    -0.63
     ProtoMessage
    -0.63
    POSITIVE LOGITS
    howto
    0.95
     how
    0.86
     如何
    0.85
    如何
    0.82
     Cómo
    0.80
     איך
    0.76
     cómo
    0.74
    怎么
    0.73
     How
    0.72
     كيفية
    0.72
    Activations Density 0.104%

    No Known Activations