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. 3-GEMMASCOPE-RES-16K
    6. 13062
    Prev
    Next
    INDEX
    Explanations

    references to 'params' and related parameter handling concepts in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rsiniz
    -0.95
    LookAnd
    -0.86
     فريبيس
    -0.79
     SafeMath
    -0.79
     Luch
    -0.79
    circledR
    -0.76
     tartalomajánló
    -0.75
    *{-
    -0.74
     waitFor
    -0.73
     contextLoads
    -0.72
    POSITIVE LOGITS
    params
    3.01
     params
    2.81
    Params
    2.29
     Params
    1.93
    getParams
    1.67
    PARAMS
    1.61
    Param
    1.10
     useParams
    1.02
    PARAM
    1.01
    param
    1.01
    Activations Density 0.045%

    No Known Activations