© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105952
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or information

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

    Common phrases in technical help requests expressing needs, describing problems, and soliciting assistance, often with politeness markers.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     itſelf
    -0.68
     المعيارى
    -0.59
    dafx
    -0.57
    ſelf
    -0.55
     disponibilités
    -0.55
     myſelf
    -0.54
    UnsafeEnabled
    -0.53
    ėmis
    -0.53
    ніципа
    -0.51
     дописавши
    -0.49
    POSITIVE LOGITS
     legal
    0.39
    enchymal
    0.38
     légale
    0.37
     Mühl
    0.37
     légal
    0.37
     Antonio
    0.36
     Viena
    0.36
    AdapterView
    0.35
     peuple
    0.35
     Schindler
    0.35
    Activations Density 0.110%

    No Known Activations