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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 65011
    Prev
    Next
    INDEX
    Explanations

    conditional statements and specific mathematical terms related to evaluations and criteria

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

    natural availability

    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
    ']}
    -0.31
     merk
    -0.28
    ]<<"
    -0.28
     stehen
    -0.28
    ographiques
    -0.27
    Board
    -0.27
     participaron
    -0.27
    發
    -0.26
     funcione
    -0.26
    hon
    -0.26
    POSITIVE LOGITS
     للاسماء
    0.65
    AndroidJUnit
    0.64
    ⟬
    0.62
    featureID
    0.57
     ErrIntOverflow
    0.56
    itattu
    0.56
     transfieras
    0.55
    yntaxException
    0.54
    出版年
    0.53
    SBATCH
    0.53
    Activations Density 0.335%

    No Known Activations