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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9255
    Prev
    Next
    INDEX
    Explanations

    actions involving raising or moving hands and interacting with other subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     gynnwys
    -0.62
    contentLoaded
    -0.50
    łaś
    -0.49
     fallu
    -0.48
     terle
    -0.45
     مفص
    -0.44
    theoremstyle
    -0.44
     skór
    -0.44
    igslist
    -0.44
    Obrázky
    -0.44
    POSITIVE LOGITS
     hands
    1.52
     hand
    1.35
    hands
    1.32
     fingers
    1.25
     Hands
    1.24
    Hands
    1.22
     finger
    1.19
     HANDS
    1.18
     arms
    1.16
    hand
    1.16
    Activations Density 0.182%

    No Known Activations