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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 123692
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate purpose or reason, particularly those beginning with "for."

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

    make/provide for noun phrase

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Viited
    -0.51
    Portale
    -0.43
    InjectAttribute
    -0.40
    lccn
    -0.39
    DAOImpl
    -0.38
    ExtendWith
    -0.38
    Varint
    -0.37
    Externí
    -0.34
     ese
    -0.34
     punta
    -0.33
    POSITIVE LOGITS
    addContainerGap
    0.55
    PageFactory
    0.52
     occaf
    0.52
    éez
    0.51
    odend
    0.49
     dortmund
    0.48
    Makes
    0.48
     Makes
    0.48
     Stirn
    0.47
    Made
    0.47
    Activations Density 0.010%

    No Known Activations