© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3396
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases associated with actions or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DJANGO
    -0.62
    esModule
    -0.58
    everybody
    -0.57
    stdafx
    -0.56
     gainera
    -0.55
    IBOutlet
    -0.54
    Everybody
    -0.54
     everybody
    -0.53
     protoimpl
    -0.50
     you
    -0.50
    POSITIVE LOGITS
    ArrowToggle
    0.93
     utafitiHapana
    0.66
     autorytatywna
    0.65
    נם
    0.58
     ſever
    0.57
     defStyle
    0.57
    chede
    0.57
     Geraldine
    0.57
     sibi
    0.56
     Moderato
    0.56
    Activations Density 0.283%

    No Known Activations