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. 90740
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or conditions related to scientific measurements or classifications

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

    neurons, synthases, DA2, CT116, RO2138/6-1

    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
    atimes
    -0.52
    crollView
    -0.52
    رشف
    -0.47
    nofollow
    -0.46
     estekak
    -0.46
    弦
    -0.46
     snob
    -0.46
     relations
    -0.46
     urin
    -0.46
     grad
    -0.45
    POSITIVE LOGITS
     dumne
    0.63
     picioare
    0.53
     îna
    0.51
    ThroughAttribute
    0.50
     maș
    0.50
     creș
    0.45
     nivelul
    0.44
     utford
    0.42
     nemlig
    0.42
     typelib
    0.42
    Activations Density 0.325%

    No Known Activations