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. 15-GEMMASCOPE-RES-16K
    6. 8615
    Prev
    Next
    INDEX
    Explanations

    terms related to data transfer and connection in electronic systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.55
     الرياضيه
    -0.55
    */),
    -0.46
    netbeans
    -0.45
     بيها
    -0.44
    Nuorodos
    -0.43
    EndContext
    -0.43
     Отечественной
    -0.41
    UserScript
    -0.40
    ลูก
    -0.40
    POSITIVE LOGITS
     source
    0.88
     sources
    0.80
    بوابة
    0.76
    IntoConstraints
    0.74
     Italijanski
    0.72
    source
    0.69
     fuente
    0.69
     fonte
    0.68
     sourced
    0.66
    源
    0.65
    Activations Density 0.585%

    No Known Activations