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. 4-GEMMASCOPE-RES-16K
    6. 11062
    Prev
    Next
    INDEX
    Explanations

    references to session and post parameters in PHP code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.95
    onOptions
    -0.70
    enumi
    -0.70
     defStyle
    -0.68
    στ
    -0.68
     OFDb
    -0.67
     estimés
    -0.67
    väg
    -0.65
     WISH
    -0.64
    HtmlAttribute
    -0.63
    POSITIVE LOGITS
    SESSION
    2.55
     SESSION
    0.88
     session
    0.79
     sessions
    0.65
     Session
    0.64
    sessionId
    0.63
    Session
    0.62
     EventArgs
    0.61
    ession
    0.61
    session
    0.60
    Activations Density 0.031%

    No Known Activations