© 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
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2231
    Prev
    Next
    INDEX
    Explanations

    verbs related to the act of creating or initiating new entities or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $_[
    -0.68
     $_(
    -0.67
     errMsg
    -0.66
     jsonObj
    -0.65
     DialogInterface
    -0.63
     nakalista
    -0.61
     Tongue
    -0.60
     onResume
    -0.59
    ioutil
    -0.59
     ioutil
    -0.59
    POSITIVE LOGITS
    create
    1.26
     create
    1.23
     creation
    1.16
     Create
    1.14
     created
    1.13
    Create
    1.12
     Creation
    1.07
     CREATE
    1.03
     créer
    1.02
    CREATE
    1.02
    Activations Density 0.075%

    No Known Activations