© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 672
    Prev
    Next
    INDEX
    Explanations

    technical terms related to digital systems and signal strength management

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

    numerical information related to power and energy usage

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

    strength and intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.70
    ########.
    -0.67
     HasFactory
    -0.66
    __))
    -0.63
    RectangleBorder
    -0.59
    alloon
    -0.59
     invitamos
    -0.57
     offside
    -0.56
     TextInputType
    -0.56
    ollection
    -0.56
    POSITIVE LOGITS
     strength
    1.58
     intensity
    1.37
    strength
    1.36
     stronger
    1.34
     strongest
    1.29
     Strength
    1.24
    Strength
    1.20
     strong
    1.20
     STRENGTH
    1.18
     Intensity
    1.17
    Activations Density 0.484%

    No Known Activations