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. 24-GEMMASCOPE-RES-16K
    6. 8262
    Prev
    Next
    INDEX
    Explanations

    technical or mechanical processes and actions

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

    Cause and effect relationships

    np_acts-logits-general · gemini-2.0-flash

    movement, release, or passage of substances

    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
    ConstraintMaker
    -0.56
    WarningLevel
    -0.49
    plotlib
    -0.48
     pinggang
    -0.48
     fournisseurs
    -0.47
    IsMutable
    -0.46
     modalités
    -0.46
    clerview
    -0.46
     semej
    -0.45
     Gesundheits
    -0.45
    POSITIVE LOGITS
     moisture
    1.02
     excess
    0.94
     air
    0.93
     dirt
    0.92
     debris
    0.88
     saliva
    0.87
     nutrients
    0.86
     fluids
    0.85
     airflow
    0.83
     toxins
    0.83
    Activations Density 0.732%

    No Known Activations