Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 3713
    Prev
    Next
    INDEX
    Explanations

    concepts related to identification and universal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.62
    forChild
    -0.53
    IUrlHelper
    -0.52
    krieg
    -0.48
    ytä
    -0.48
    saf
    -0.48
     quyết
    -0.48
     llaman
    -0.47
    رشف
    -0.45
    ozof
    -0.45
    POSITIVE LOGITS
     relatable
    0.81
     empathi
    0.74
     sympathize
    0.73
     TextAppearance
    0.73
     sympathetic
    0.67
    ArgsConstructor
    0.67
     sympathi
    0.67
     vécu
    0.66
     sympathy
    0.65
     vivió
    0.64
    Activations Density 0.171%

    No Known Activations