© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13020
    Prev
    Next
    INDEX
    Explanations

    instances of emotional dialogue or expressions of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GLOBALS
    -0.55
     thyself
    -0.53
    νης
    -0.52
     itſelf
    -0.50
    orist
    -0.50
    intérêt
    -0.50
     Schools
    -0.49
    Schools
    -0.49
    CVS
    -0.49
     schools
    -0.49
    POSITIVE LOGITS
    BeginInit
    0.86
    webElementXpaths
    0.68
    SharedCtor
    0.61
    LookAnd
    0.60
    memoized
    0.58
    verwijspagina
    0.58
     ostavi
    0.57
    colhead
    0.57
     externes
    0.57
    FieldNumber
    0.55
    Activations Density 0.112%

    No Known Activations