© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105957
    Prev
    Next
    INDEX
    Explanations

    references to living arrangements and virtual computing resources

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

    apartment, apartments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    出现了
    -0.33
    posedge
    -0.33
     sih
    -0.32
     involuntary
    -0.31
     attribute
    -0.31
    imp
    -0.31
     ami
    -0.30
     attributes
    -0.30
    AttributeValue
    -0.30
     Akti
    -0.30
    POSITIVE LOGITS
     ujednoznacz
    0.73
    rungsseite
    0.69
    تقاوى
    0.68
     protoimpl
    0.65
    providedIn
    0.65
     ProtoMessage
    0.63
     صوتيه
    0.61
    новниш
    0.58
    DockStyle
    0.57
     utafitiHapana
    0.57
    Activations Density 0.006%

    No Known Activations