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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10760
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Grasping, holding, or ergonomic features

    np_acts-logits-general · gemini-2.0-flash

    grip and handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     undef
    -0.53
     diplomacy
    -0.52
     Wyn
    -0.51
    aigu
    -0.50
     supersonic
    -0.48
     rasc
    -0.48
     automata
    -0.47
     tabulation
    -0.46
     diaphragm
    -0.46
     Automata
    -0.46
    POSITIVE LOGITS
     grip
    1.51
     grips
    1.33
     Grip
    1.25
    grip
    1.20
     hold
    1.15
    Grip
    1.13
     gripping
    1.12
     gripped
    1.09
    hold
    1.07
     handles
    1.06
    Activations Density 0.259%

    No Known Activations