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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 5954
    Prev
    Next
    INDEX
    Explanations

    technical details regarding electronic circuit components and their configurations

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

    "resistance", "capacitor", and circuit elements

    np_acts-logits-general · gemini-2.0-flash

    resistance and pf cap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MethodManager
    -0.66
     Audiodateien
    -0.65
    riebene
    -0.60
    μένες
    -0.56
    rawDesc
    -0.54
     demografica
    -0.54
     crack
    -0.53
    riebenen
    -0.53
     MainAxisSize
    -0.53
    GeoNames
    -0.53
    POSITIVE LOGITS
     resistance
    1.33
     Resistance
    1.24
    Resistance
    1.19
     Resist
    1.10
    resistance
    1.08
     RESISTANCE
    1.08
     resistances
    1.05
    Resist
    1.04
     resistencia
    0.99
     resistor
    0.96
    Activations Density 0.359%

    No Known Activations