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. 6829
    Prev
    Next
    INDEX
    Explanations

    references to specific anime titles and related content

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

    after capitalized words or titles

    np_acts-logits-general · gemini-2.0-flash

    Matrix, pill, Neo

    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
     poivre
    -0.41
     drapeau
    -0.40
     boste
    -0.37
     yumu
    -0.37
     nač
    -0.35
     dedicado
    -0.35
     Menschheit
    -0.35
    Clik
    -0.34
     Clippers
    -0.34
    organ
    -0.34
    POSITIVE LOGITS
    matchCondition
    0.59
     TestBed
    0.56
     iprot
    0.56
     NEO
    0.52
    ésult
    0.50
     viewDidLoad
    0.49
    tanleria
    0.48
     Neo
    0.47
    EDEFAULT
    0.47
    jsonwebtoken
    0.47
    Activations Density 0.582%

    No Known Activations