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. 151
    Prev
    Next
    INDEX
    Explanations

    specific programming syntax and structure related to user interface elements

    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
    RequestMapping
    -0.38
    ControllerAdvice
    -0.35
     CGPoint
    -0.35
     TRA
    -0.32
     reprodu
    -0.32
     getPosition
    -0.31
    OutOfRange
    -0.31
     posX
    -0.31
     FileNotFound
    -0.30
     population
    -0.29
    POSITIVE LOGITS
    OGND
    0.65
     nakalista
    0.65
    AnchorStyles
    0.64
     <<<<<<<<<<<<<<
    0.54
    inSlope
    0.52
    ípios
    0.51
     kaarangay
    0.49
    Portail
    0.49
     Wicidata
    0.48
     الحره
    0.48
    Activations Density 0.208%

    No Known Activations