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. 6797
    Prev
    Next
    INDEX
    Explanations

    technical requests or questions regarding software development

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

    Following "to" and verb for an action

    np_acts-logits-general · gemini-2.0-flash

    create or build something

    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
     ویکی‌پدیا
    -0.55
     defaultstate
    -0.50
    Jeografia
    -0.48
    AccessorTable
    -0.47
    ConstraintMaker
    -0.46
    MessageState
    -0.46
    Morfologia
    -0.46
    فحة
    -0.45
    +#+
    -0.44
    الدراسه
    -0.44
    POSITIVE LOGITS
    forRoot
    0.42
     afspraak
    0.36
     싶
    0.35
    Dsl
    0.33
     biar
    0.33
    TintMode
    0.33
    ItemBackground
    0.33
    OGND
    0.33
    ningss
    0.32
    anned
    0.31
    Activations Density 1.335%

    No Known Activations