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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122880
    Prev
    Next
    INDEX
    Explanations

    references to specific mythical creatures and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.55
    хьтан
    -0.52
     nakalista
    -0.51
     defStyleAttr
    -0.51
     queſta
    -0.48
     autorytatywna
    -0.48
     المعيارى
    -0.48
    цездатний
    -0.48
    BASEPATH
    -0.48
     estekak
    -0.47
    POSITIVE LOGITS
     terrifying
    0.47
     monster
    0.45
     hybrid
    0.42
     frightening
    0.40
     monsters
    0.40
    spawn
    0.39
    hybrid
    0.39
     monstrous
    0.38
     resembled
    0.36
    kind
    0.36
    Activations Density 0.070%

    No Known Activations