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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14974
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and reflections

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

    following "to"

    np_acts-logits-general · gemini-2.0-flash

    useful to improve fuel

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     iprot
    -0.39
     gustado
    -0.35
    PDOException
    -0.35
    findpost
    -0.32
    CloseOperation
    -0.31
     facilita
    -0.31
     Italijanski
    -0.31
     MessageBoxIcon
    -0.30
     Gazette
    -0.30
     constaté
    -0.29
    POSITIVE LOGITS
    迎
    0.52
    MemoryWarning
    0.48
     nahilalakip
    0.47
    extAlignment
    0.47
    Toward
    0.47
     ͡°)
    0.46
    Mainly
    0.45
    BufferException
    0.44
    Towards
    0.44
    toward
    0.44
    Activations Density 0.599%

    No Known Activations