© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    statements regarding representation and perspectives of individuals or entities

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

    phrases related to official positions or policies

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

    stance or policy viewpoint

    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
     TextInputType
    -0.66
     nakalista
    -0.65
     HttpNotFound
    -0.61
    rungsseite
    -0.58
     uncin
    -0.55
    berdayakan
    -0.54
     táctil
    -0.54
     visuelle
    -0.53
    audiovisuel
    -0.53
    ImageContext
    -0.51
    POSITIVE LOGITS
     position
    2.25
     Position
    1.92
     positions
    1.85
    position
    1.84
     stance
    1.77
     POSITION
    1.74
    Position
    1.66
     Positions
    1.58
     posición
    1.57
     posição
    1.55
    Activations Density 0.446%

    No Known Activations