© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1615
    Prev
    Next
    INDEX
    Explanations

    terms related to programming, particularly C/C++ syntax and CUDA-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     المعيارى
    -0.74
     transfieras
    -0.72
     חיצוניים
    -0.69
    MLLoader
    -0.66
    rénées
    -0.64
    StructEnd
    -0.62
    extAlignment
    -0.59
    первых
    -0.58
    \{\\
    -0.58
    abstractmethod
    -0.58
    POSITIVE LOGITS
     diſt
    0.67
     ſtate
    0.65
     fhew
    0.64
     uſe
    0.63
     ſtand
    0.61
    neſs
    0.61
    المراجع
    0.61
     cauſe
    0.60
     reaſon
    0.59
     caufe
    0.59
    Activations Density 3.849%

    No Known Activations