Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15596
    Prev
    Next
    INDEX
    Explanations

    instances of the word "establish" and its derived forms

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

    "establish" or its variations

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.62
    ########.
    -0.58
     estekak
    -0.55
    
    -0.55
    Tembelea
    -0.53
    migrationBuilder
    -0.52
     IFTT
    -0.51
    ⓧ
    -0.49
    QMetaType
    -0.49
    rungsseite
    -0.49
    POSITIVE LOGITS
     établie
    0.73
     established
    0.72
     establish
    0.71
     Establish
    0.71
    Establish
    0.70
     Establishing
    0.68
     establishes
    0.67
     establishing
    0.67
     ESTABL
    0.66
    established
    0.66
    Activations Density 0.066%

    No Known Activations