© 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. 23-GEMMASCOPE-RES-16K
    6. 9263
    Prev
    Next
    INDEX
    Explanations

    numeric time representations and schedule-related terms

    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
     Vikipedi
    -0.84
     AssemblyProduct
    -0.73
     resourceCulture
    -0.67
    ----</
    -0.66
     Normdatei
    -0.64
    EndInit
    -0.64
    ).__
    -0.63
    ParallelGroup
    -0.62
    SPJ
    -0.61
    <()>
    -0.61
    POSITIVE LOGITS
    pm
    1.20
     pm
    1.15
     PM
    1.04
    PM
    1.03
    am
    0.81
    AM
    0.77
     AM
    0.77
     am
    0.75
    Pm
    0.70
     p
    0.66
    Activations Density 0.147%

    No Known Activations