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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 86132
    Prev
    Next
    INDEX
    Explanations

    components related to accessibility features and pagination in user interface code

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

    Pagination and enhancer concepts

    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
    pagination
    -0.59
     Commence
    -0.41
    — 
    -0.40
    iastes
    -0.39
    ******/
    -0.39
     fopen
    -0.39
    ondheim
    -0.38
     Drop
    -0.37
    Klem
    -0.37
     drop
    -0.36
    POSITIVE LOGITS
    Pagination
    1.52
    hancer
    0.96
     Pagination
    0.96
    hancers
    0.74
    withOpacity
    0.64
     يتيمه
    0.63
    sizeCache
    0.63
     CanadaChoose
    0.62
    rungsseite
    0.61
    ltk
    0.60
    Activations Density 0.001%

    No Known Activations