© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 76747
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and relationships related to statistical moments and probability distributions

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

    mathematical expectation

    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
    SharedCtor
    -0.71
     linkovi
    -0.57
    ValueStyle
    -0.55
    igshid
    -0.50
     sumpay
    -0.47
    يكب
    -0.47
    interopRequire
    -0.47
     Audiodateien
    -0.46
     Normdatei
    -0.46
     <<<<<<<<<<<<<<
    -0.45
    POSITIVE LOGITS
     expectation
    0.81
    Expectation
    0.72
    expectation
    0.69
     Expectation
    0.65
     expectations
    0.60
     expectativa
    0.58
     expectativas
    0.55
     expected
    0.54
    expectations
    0.52
     Erwart
    0.52
    Activations Density 0.470%

    No Known Activations