© 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. 40-GEMMASCOPE-RES-16K
    6. 6085
    Prev
    Next
    INDEX
    Explanations

    terms related to functional classifications and properties in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     funding
    -0.54
     funcionales
    -0.52
     fonction
    -0.49
    SourceChecksum
    -0.49
    FUNDING
    -0.48
     fungsi
    -0.47
     функций
    -0.46
    Funding
    -0.46
     jspb
    -0.46
     funzione
    -0.45
    POSITIVE LOGITS
    ALITY
    0.61
    ality
    0.57
    tional
    0.57
    alities
    0.56
    lity
    0.54
    alised
    0.53
    bootstrapcdn
    0.51
    aries
    0.50
    tionally
    0.50
    nloa
    0.50
    Activations Density 0.234%

    No Known Activations