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. 17-GEMMASCOPE-RES-16K
    6. 5100
    Prev
    Next
    INDEX
    Explanations

    thoughts and reflections related to listening and consideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.80
     صوتيه
    -0.80
     виправивши
    -0.78
     Paglinawan
    -0.73
     Italijanski
    -0.72
    Parcelize
    -0.71
    astify
    -0.68
    enumi
    -0.66
    jspb
    -0.66
     الحره
    -0.66
    POSITIVE LOGITS
     about
    0.70
    jooq
    0.58
     liné
    0.48
     respeito
    0.47
     berita
    0.47
     noires
    0.47
     lot
    0.46
     ouvertes
    0.46
     up
    0.45
     pleins
    0.45
    Activations Density 0.133%

    No Known Activations