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. 2-GEMMASCOPE-RES-16K
    6. 3593
    Prev
    Next
    INDEX
    Explanations

    elements related to HTTP request and response handling, particularly around body content and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lähteet
    -0.68
    ReusableCell
    -0.58
    헌
    -0.53
    CloseOperation
    -0.52
    verwijspagina
    -0.49
     Superhosts
    -0.49
    Obrázky
    -0.49
     espèce
    -0.47
    CodeDom
    -0.47
    BuildContext
    -0.45
    POSITIVE LOGITS
    SourceChecksum
    0.68
    chapper
    0.66
     FormData
    0.62
    Notae
    0.61
     /\.
    0.60
    URLConnection
    0.60
    RequestBody
    0.60
     ContentValues
    0.59
     nahilalakip
    0.59
     beginnetje
    0.57
    Activations Density 0.926%

    No Known Activations