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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10805
    Prev
    Next
    INDEX
    Explanations

    terms related to biological conditions and their implications

    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
     şi
    -1.27
     centralised
    -1.22
    Colour
    -1.20
    coloured
    -1.19
     utilisation
    -1.16
     realise
    -1.16
     generalised
    -1.16
     realises
    -1.15
     realised
    -1.15
     unauthorised
    -1.14
    POSITIVE LOGITS
     theaters
    1.49
     flavors
    1.49
     Ее
    1.47
     fibers
    1.43
     theater
    1.38
     flavor
    1.34
     molds
    1.34
     catalogs
    1.32
     endeavored
    1.31
     parlor
    1.31
    Activations Density 0.672%

    No Known Activations