© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10367
    Prev
    Next
    INDEX
    Explanations

    actions involving pulling

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

    "pull" or "pulling"

    np_acts-logits-general · gemini-2.0-flash

    pull

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    دانشنامهٔ
    -0.45
    zzleHttp
    -0.44
     ivelany
    -0.35
    feinander
    -0.34
    formik
    -0.34
     hóa
    -0.34
    fVar
    -0.33
     leksikon
    -0.33
    AsUp
    -0.33
    الدراسه
    -0.33
    POSITIVE LOGITS
     pull
    2.22
    pull
    2.16
     Pull
    2.14
    Pull
    2.06
     pulling
    2.02
     pulled
    2.02
     PULL
    2.02
     pulls
    2.02
     Pulling
    1.97
    pulled
    1.93
    Activations Density 0.169%

    No Known Activations