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. 1516
    Prev
    Next
    INDEX
    Explanations

    references to articles and essays, particularly in academic or journalistic contexts

    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
    SerializeField
    -0.55
    adə
    -0.52
     متعلقه
    -0.51
    CGContext
    -0.51
    approximate
    -0.48
     avenge
    -0.47
    iffa
    -0.47
     TAMBÉM
    -0.47
     femininos
    -0.46
     IBOutlet
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.76
    Personendaten
    0.70
     entitled
    0.69
    GTCX
    0.59
     published
    0.57
    gonic
    0.57
     titled
    0.56
     dated
    0.56
    addGap
    0.55
     containing
    0.55
    Activations Density 0.725%

    No Known Activations