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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4200
    Prev
    Next
    INDEX
    Explanations

    terms related to identification and categorization of entities and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/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.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dır
    -0.83
    d
    -0.73
    dress
    -0.71
    down
    -0.66
    governmental
    -0.65
    ders
    -0.64
    dog
    -0.64
    da
    -0.63
    daten
    -0.63
    durch
    -0.63
    POSITIVE LOGITS
    nnnn
    0.80
    ning
    0.79
    ned
    0.74
    nnn
    0.74
    ized
    0.69
    ization
    0.67
    NNNN
    0.66
    ize
    0.66
    izing
    0.64
    netje
    0.64
    Activations Density 1.673%

    No Known Activations