© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2224
    Prev
    Next
    INDEX
    Explanations

    terms related to the measurement and analysis of physiological conditions and data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.67
    parsedMessage
    -0.65
    ftagPool
    -0.63
    MessageOf
    -0.63
     OFDb
    -0.60
     itſelf
    -0.57
     يتيمه
    -0.55
    Autoritní
    -0.54
    EndGlobalSection
    -0.52
    WriteBarrier
    -0.51
    POSITIVE LOGITS
    OOTDTY
    0.42
    THANK
    0.37
    Priv
    0.36
    vraagd
    0.36
    paž
    0.35
    więcej
    0.35
    úmer
    0.35
     Ciencia
    0.35
     enak
    0.34
     Spuren
    0.34
    Activations Density 1.315%

    No Known Activations