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. 77193
    Prev
    Next
    INDEX
    Explanations

    specific code constructs and programming-related terms within the text

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

    numbers and codes

    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
     Houſe
    -0.58
     Normdatei
    -0.57
    findpost
    -0.54
    Хьажоргаш
    -0.50
     ſche
    -0.49
     estekak
    -0.49
    Enllaces
    -0.49
    inWeight
    -0.49
     ſtate
    -0.48
    minton
    -0.48
    POSITIVE LOGITS
     code
    0.43
    code
    0.42
     Svensson
    0.41
    redraw
    0.38
     Wolff
    0.38
    quester
    0.38
     recomienda
    0.36
    pic
    0.36
    wor
    0.36
     Lindgren
    0.36
    Activations Density 0.497%

    No Known Activations