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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6800
    Prev
    Next
    INDEX
    Explanations

    expressions of value or worth regarding experiences or actions

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

    Immediately precedes "it" or "your"

    np_acts-logits-general · gemini-2.0-flash

    is it worth

    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
     coque
    -0.37
     tranſ
    -0.35
     nomme
    -0.34
     évolu
    -0.34
     fermée
    -0.34
     fermé
    -0.34
     rå
    -0.34
    opengl
    -0.33
    fromJson
    -0.32
    อา
    -0.32
    POSITIVE LOGITS
     worth
    1.70
    Worth
    1.58
     Worth
    1.56
     WORTH
    1.48
    worth
    1.37
    WORTH
    1.25
     worthwhile
    1.11
     lohnt
    1.05
    值得
    1.03
     Worthy
    1.02
    Activations Density 0.141%

    No Known Activations