© 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. 24-GEMMASCOPE-RES-16K
    6. 12593
    Prev
    Next
    INDEX
    Explanations

    mentions of specific formal communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text within brackets and quotations

    np_acts-logits-general · gemini-2.0-flash

    asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.87
    quartered
    -0.60
    uttavia
    -0.60
    loroethane
    -0.56
    LookAnd
    -0.55
     thereupon
    -0.54
    abestanden
    -0.53
     therefor
    -0.53
    writeField
    -0.51
     individually
    -0.51
    POSITIVE LOGITS
     Why
    0.98
     How
    0.94
     why
    0.91
    Why
    0.88
     how
    0.85
    How
    0.83
     Meet
    0.80
     Cómo
    0.75
     Former
    0.74
     What
    0.74
    Activations Density 0.096%

    No Known Activations