© 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. 825
    Prev
    Next
    INDEX
    Explanations

    instances of the word "speak" and its variations, indicating discussion or communication

    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
    原始内容存档于
    -0.40
    faithful
    -0.38
    InputBorder
    -0.38
    insegna
    -0.38
    oma
    -0.34
    łoż
    -0.33
     Hammer
    -0.32
    CHR
    -0.32
    Hvordan
    -0.32
    gering
    -0.32
    POSITIVE LOGITS
     volumes
    0.79
     truth
    0.78
     fluent
    0.73
     highly
    0.73
     Highly
    0.66
    Highly
    0.66
     louder
    0.65
     Volumes
    0.64
    highly
    0.63
     CURIAM
    0.63
    Activations Density 0.151%

    No Known Activations