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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 6593
    Prev
    Next
    INDEX
    Explanations

    references to mistakes and errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pecto
    -0.44
     الجد
    -0.43
     للمعارف
    -0.43
     oprot
    -0.41
    EncBinary
    -0.41
     الشع
    -0.41
    enforce
    -0.40
     Dostupné
    -0.40
     harten
    -0.40
    cillor
    -0.40
    POSITIVE LOGITS
     mistakes
    1.30
     Mistakes
    1.20
     errors
    1.13
     mistake
    1.13
     Fehler
    1.12
     defects
    1.10
     faults
    1.09
     Errors
    1.06
     Defects
    1.02
     defect
    0.99
    Activations Density 0.467%

    No Known Activations