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. 108801
    Prev
    Next
    INDEX
    Explanations

    references to technical concepts and specifications in software development

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

    command line tools

    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
     Geſch
    -1.15
     Geſ
    -1.13
    <unused74>
    -1.11
    parsedMessage
    -1.11
    <unused52>
    -1.11
    <unused41>
    -1.11
    <unused14>
    -1.10
    <unused16>
    -1.10
    <unused8>
    -1.10
    [@BOS@]
    -1.10
    POSITIVE LOGITS
    <code>
    0.56
    I
    0.50
    0
    0.49
    <blockquote>
    0.46
    My
    0.45
     I
    0.45
    2
    0.44
    1
    0.44
    <i>
    0.44
    ↵
    0.42
    Activations Density 0.202%

    No Known Activations