© 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. 1378
    Prev
    Next
    INDEX
    Explanations

    references to user profiles or contact points

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

    phrases associated with profile elements and points of contact

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

    punto or set followed by words or symbols

    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
    Personensuche
    -0.74
    complexContent
    -0.72
     Monfieur
    -0.71
    ArgsConstructor
    -0.60
    __":
    -0.59
     esternos
    -0.59
     Normdatei
    -0.58
    dafx
    -0.58
    __":
    -0.58
    orianCalendar
    -0.57
    POSITIVE LOGITS
    -
    0.78
     kunci
    0.51
    leit
    0.48
    -\
    0.46
     chi
    0.45
     clave
    0.45
    –
    0.45
    Homework
    0.43
    edere
    0.43
    ->___
    0.43
    Activations Density 0.072%

    No Known Activations