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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14810
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate simultaneous actions or conditions

    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
    ніципалі
    -0.59
    Geografi
    -0.53
    */
    -0.50
    msgid
    -0.48
    them
    -0.47
    where
    -0.47
     /\.
    -0.46
    ธ์
    -0.45
    him
    -0.44
    fiddle
    -0.44
    POSITIVE LOGITS
     they
    1.10
     still
    1.08
     simultaneously
    1.05
     others
    0.99
    still
    0.95
     awaiting
    0.93
     we
    0.93
     nahilalakip
    0.87
     OTHERS
    0.81
     also
    0.81
    Activations Density 0.077%

    No Known Activations