© 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 - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 110610
    Prev
    Next
    INDEX
    Explanations

    key actions and decisions related to job offers

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

    job offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    UnusedPrivate
    -0.46
    setVerticalGroup
    -0.46
    erals
    -0.42
    спла
    -0.41
    saraba
    -0.41
    seye
    -0.39
    AddressBook
    -0.39
    register
    -0.38
     lenker
    -0.38
     GetEnumerator
    -0.37
    POSITIVE LOGITS
    Offer
    1.17
     offer
    1.13
     Offer
    1.12
    offer
    1.12
     Offers
    0.98
    OFFER
    0.98
     OFFER
    0.96
    offers
    0.96
    Offers
    0.95
     offers
    0.94
    Activations Density 0.052%

    No Known Activations