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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 4147
    Prev
    Next
    INDEX
    Explanations

    aspects related to historical timelines and dates

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

    time or sequence

    np_acts-logits-general · gemini-2.0-flash

    temporal sequences and time periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -0.72
     combineReducers
    -0.69
    
    -0.68
     للاسماء
    -0.66
    UserScript
    -0.65
     useAuth
    -0.65
    tvguidetime
    -0.63
    Filmografia
    -0.61
     defaultstate
    -0.58
    Espèce
    -0.57
    POSITIVE LOGITS
     when
    0.96
     before
    0.94
    before
    0.93
    when
    0.92
     during
    0.91
    during
    0.90
    after
    0.83
     after
    0.82
     BEFORE
    0.79
     year
    0.78
    Activations Density 0.262%

    No Known Activations