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. 85680
    Prev
    Next
    INDEX
    Explanations

    mentions of SD and micro SD cards and their specifications

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

    SD card file operations

    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
     duração
    -0.41
     target
    -0.39
     final
    -0.37
     norm
    -0.34
     nat
    -0.33
     PAINTING
    -0.32
     painting
    -0.32
     BEGIN
    -0.32
     mål
    -0.32
     leading
    -0.31
    POSITIVE LOGITS
    TypedDataSet
    0.67
     tartalomajánló
    0.64
     microSD
    0.63
    OGND
    0.61
     estekak
    0.61
     Exacts
    0.60
    imageshack
    0.60
    Tikang
    0.57
     HasFactory
    0.52
    fjspx
    0.51
    Activations Density 0.006%

    No Known Activations