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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15633
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and geometric parameters related to angles and rotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    чеб
    -0.53
    __()
    -0.49
     emp
    -0.48
    Abitanti
    -0.47
     lac
    -0.47
     المعيارى
    -0.46
    сси
    -0.46
    ystis
    -0.44
    客
    -0.44
     inst
    -0.43
    POSITIVE LOGITS
     Efq
    0.83
     angles
    0.83
     fevere
    0.80
     angle
    0.78
     ángulo
    0.77
     ſhe
    0.76
     Monfieur
    0.75
     radians
    0.73
     aveug
    0.72
     ſever
    0.72
    Activations Density 0.484%

    No Known Activations