© 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. 9-GEMMASCOPE-RES-131K
    11. 20018
    Prev
    Next
    INDEX
    Explanations

    references to white powdery substances and their containment in some kind of packet

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

    physical forms and things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.55
    Cyfarwyddwr
    -0.53
     kasarigan
    -0.52
    homonymie
    -0.51
     estekak
    -0.50
    ̈́
    -0.49
    ScopeManager
    -0.48
     kaynağından
    -0.47
     كومونز
    -0.47
    principalColumn
    -0.46
    POSITIVE LOGITS
     thingy
    0.54
     thing
    0.52
     mysterious
    0.50
     THING
    0.48
     resembling
    0.48
     Thing
    0.47
     ressemb
    0.47
    sterious
    0.46
     Thad
    0.45
     ressemble
    0.45
    Activations Density 0.405%

    No Known Activations