© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 15965
    Prev
    Next
    INDEX
    Explanations

    specific phrases and terms related to scientific measurements and properties

    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
    SequentialGroup
    -0.61
     <=",
    -0.56
    SuppressLint
    -0.56
    HasAnnotation
    -0.56
    ImageContext
    -0.55
    bootstrapcdn
    -0.52
     समीक्षाओं
    -0.50
    MessageTagHelper
    -0.50
    Datuak
    -0.50
    IBOutlet
    -0.49
    POSITIVE LOGITS
     AssemblyCulture
    0.46
     initComponents
    0.37
     Underground
    0.36
     attack
    0.35
     of
    0.35
     intr
    0.35
     each
    0.35
     bon
    0.34
    Unsigned
    0.34
     components
    0.34
    Activations Density 1.413%

    No Known Activations