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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14910
    Prev
    Next
    INDEX
    Explanations

    terms related to mapping, measuring, and referencing data in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.73
     Савезне
    -0.73
    tonode
    -0.59
     Италијани
    -0.57
    tagHelperRunner
    -0.56
     виправивши
    -0.55
     GoogleFonts
    -0.54
    transQ
    -0.50
    parsedMessage
    -0.50
    تقاوى
    -0.46
    POSITIVE LOGITS
     ujednoznacz
    0.49
    Зноскі
    0.46
     Democrá
    0.44
    rests
    0.42
    IndentedString
    0.42
     redonda
    0.41
     principal
    0.41
    tees
    0.40
    AnchorStyles
    0.40
     arrivare
    0.40
    Activations Density 1.005%

    No Known Activations