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. 23-GEMMASCOPE-RES-16K
    6. 5365
    Prev
    Next
    INDEX
    Explanations

    expressions of intense emotions and sensory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ècie
    -0.70
    出版年
    -0.67
    Sortie
    -0.59
    enschaften
    -0.55
     فريبيس
    -0.54
    InputTagHelper
    -0.53
    !("{}",
    -0.53
    cambrian
    -0.53
    lysm
    -0.52
    interopRequire
    -0.52
    POSITIVE LOGITS
     shattering
    0.77
     melting
    0.72
     splitting
    0.71
    breaking
    0.67
     bust
    0.65
    melting
    0.64
     twisting
    0.63
     bending
    0.63
    splitting
    0.62
     crushing
    0.62
    Activations Density 0.173%

    No Known Activations