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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 70756
    Prev
    Next
    INDEX
    Explanations

    references to educational materials related to music and dance

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

    academic citations and numbers

    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
    HasBeenSet
    -0.37
    ďaka
    -0.36
     llaman
    -0.35
     cáps
    -0.34
     alfombra
    -0.33
    tste
    -0.33
     kepad
    -0.32
     cappuccio
    -0.32
     nemici
    -0.32
    oneg
    -0.31
    POSITIVE LOGITS
    AllAfrica
    0.50
     مشين
    0.49
    jsonwebtoken
    0.46
    SocketChannel
    0.45
     astore
    0.45
     pedagogical
    0.45
     courses
    0.44
     equity
    0.43
    VYMaps
    0.42
    IUrlHelper
    0.42
    Activations Density 0.071%

    No Known Activations