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. 9017
    Prev
    Next
    INDEX
    Explanations

    constructions involving the act of communication or storytelling

    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
     Wikipédia
    -0.69
     euer
    -0.64
    vieve
    -0.55
    itteet
    -0.53
    yarnpkg
    -0.53
    Démographie
    -0.53
    Schwer
    -0.52
     virke
    -0.52
    лә
    -0.52
    ledem
    -0.52
    POSITIVE LOGITS
     tell
    1.38
     Tells
    1.35
     Telling
    1.29
     tells
    1.29
     Tell
    1.28
     TELL
    1.28
     tale
    1.27
    Telling
    1.24
    Tell
    1.23
    tale
    1.22
    Activations Density 0.065%

    No Known Activations