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. 9-GEMMASCOPE-RES-16K
    6. 1470
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "constant" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lujah
    -0.80
    Wies
    -0.72
     незавершена
    -0.69
     utafitiHapana
    -0.69
    profen
    -0.68
    ivir
    -0.67
     FLY
    -0.67
     antaranya
    -0.67
    Numerology
    -0.67
     wigs
    -0.67
    POSITIVE LOGITS
     Constant
    1.65
     CONSTANT
    1.57
    Constant
    1.57
    CONSTANT
    1.52
     constants
    1.45
     constant
    1.45
     Constantin
    1.38
     Constants
    1.35
     Constantine
    1.30
    constant
    1.30
    Activations Density 0.059%

    No Known Activations