© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1261
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "create" and its variations indicating the act of formation or establishment

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

    verbs related to creating or generating something.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    -0.64
     jsonObj
    -0.58
     $_[
    -0.57
     $_(
    -0.57
    calaureate
    -0.53
     Tongue
    -0.52
     nakalista
    -0.51
     ioutil
    -0.50
     Opinion
    -0.49
    ioutil
    -0.49
    POSITIVE LOGITS
    create
    1.09
     create
    1.02
     created
    1.00
     Create
    0.99
     creation
    0.98
    Create
    0.98
     Creation
    0.94
     créer
    0.88
     CREATE
    0.88
     Created
    0.87
    Activations Density 0.077%

    No Known Activations