Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8353
    Prev
    Next
    INDEX
    Explanations

    terms related to HTTP request methods

    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
     Efq
    -0.80
    oredCriteria
    -0.79
    abestanden
    -0.78
     poffe
    -0.75
    cupertino
    -0.70
     themſelves
    -0.70
     tslint
    -0.69
     يتيمه
    -0.68
     fhew
    -0.68
     myſelf
    -0.67
    POSITIVE LOGITS
    method
    1.84
    Method
    1.81
     Method
    1.73
    METHOD
    1.50
     method
    1.47
     METHOD
    1.41
    getMethod
    1.07
    MethodName
    0.91
    methodName
    0.89
    isMethod
    0.88
    Activations Density 0.111%

    No Known Activations