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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 691
    Prev
    Next
    INDEX
    Explanations

    instances of the word "create" and related forms

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

    "create"

    np_acts-logits-general · gemini-2.0-flash

    create

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     errMsg
    -0.68
     $_[
    -0.68
     $_(
    -0.65
     jsonObj
    -0.60
     nakalista
    -0.57
    calaureate
    -0.56
     ioutil
    -0.56
    PMailer
    -0.54
     parlement
    -0.54
     DialogInterface
    -0.54
    POSITIVE LOGITS
    create
    1.14
     create
    1.06
     Create
    1.04
    Create
    1.02
     creation
    0.98
     created
    0.97
     Creation
    0.93
     CREATE
    0.89
    CREATE
    0.89
     créer
    0.88
    Activations Density 0.091%

    No Known Activations