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. 1-GEMMASCOPE-RES-16K
    6. 6011
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to programming and data structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    पया
    -0.79
     Monfieur
    -0.72
     vinto
    -0.58
     Theſe
    -0.58
    writeHead
    -0.57
     rius
    -0.56
    Réponse
    -0.56
     isolé
    -0.56
     puissante
    -0.56
     verbinding
    -0.56
    POSITIVE LOGITS
    TagMode
    0.78
     priori
    0.63
    RuleContext
    0.62
    DebuggerNonUser
    0.62
    TemporalType
    0.60
    reactstrap
    0.57
     protoimpl
    0.56
    AspNetCore
    0.55
    skapet
    0.54
    {%
    0.53
    Activations Density 1.889%

    No Known Activations