Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114045
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    than, compared to, opposed to, unlike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     polig
    -0.43
    liferay
    -0.40
     arşivlendi
    -0.39
    AppMethodBeat
    -0.38
     PeEnEo
    -0.37
     ciel
    -0.36
    toMatchSnapshot
    -0.36
     téléchargez
    -0.35
     appelez
    -0.35
    executeUpdate
    -0.35
    POSITIVE LOGITS
     usual
    0.64
    ########.
    0.62
     previous
    0.62
     heretofore
    0.56
     current
    0.54
     diğer
    0.54
     former
    0.53
     atuais
    0.53
     sebelumnya
    0.53
     earlier
    0.52
    Activations Density 0.086%

    No Known Activations