© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 7001
    Prev
    Next
    INDEX
    Explanations

    occurrences of letters and formal correspondence references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最快更新
    -0.49
    ihnach
    -0.48
     étoit
    -0.44
     Manchuria
    -0.44
    Hades
    -0.44
     busiest
    -0.42
     Greenville
    -0.42
    indl
    -0.42
     czeka
    -0.42
     baumwolle
    -0.42
    POSITIVE LOGITS
     letter
    1.80
     letters
    1.72
     Letter
    1.66
    Letter
    1.62
     Letters
    1.60
    Letters
    1.53
     LETTERS
    1.47
     LETTER
    1.46
    letters
    1.45
    letter
    1.40
    Activations Density 0.127%

    No Known Activations