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. 4715
    Prev
    Next
    INDEX
    Explanations

    percentages and their implications in discussions related to business or economics

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

    governed by, revolves around, dominated by

    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
    :✨
    -0.54
    cephala
    -0.52
    bootstrapcdn
    -0.50
     <>",
    -0.50
    CppMethod
    -0.49
    ochet
    -0.46
    🖐
    -0.45
    周泽
    -0.45
    omitempty
    -0.44
    acry
    -0.44
    POSITIVE LOGITS
    UnknownFields
    0.45
     Chwiliwch
    0.36
     principalmente
    0.36
     épices
    0.34
    OutOfBounds
    0.33
    snprintf
    0.33
    UnusedPrivate
    0.32
    ValuePair
    0.32
     entire
    0.31
    StringCopy
    0.31
    Activations Density 0.156%

    No Known Activations