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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 6928
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to practical advice and suggestions

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

    Tokens that precede "for."

    np_acts-logits-general · gemini-2.0-flash

    tips for

    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
     gelukkig
    -0.42
     Montes
    -0.38
    createElement
    -0.37
    Entities
    -0.37
    entities
    -0.36
    entity
    -0.35
    getEntity
    -0.35
     mẽ
    -0.35
     Entities
    -0.34
    xrTableCell
    -0.33
    POSITIVE LOGITS
     tips
    2.22
     tip
    2.13
     Tips
    2.09
     Tip
    1.97
    tips
    1.97
    Tips
    1.95
    Tip
    1.94
     TIPS
    1.81
    tip
    1.75
    TIPS
    1.63
    Activations Density 0.067%

    No Known Activations