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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16-GEMMASCOPE-RES-16K
    6. 1564
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to shaking or moving something

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

    "shake" or "shaking"

    np_acts-logits-general · gemini-2.0-flash

    shake related verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iteness
    -0.60
    hite
    -0.52
    masking
    -0.45
    idx
    -0.43
    Cain
    -0.43
     Rahul
    -0.43
    sight
    -0.43
    وم
    -0.42
    ateg
    -0.42
     mask
    -0.42
    POSITIVE LOGITS
     shakes
    1.24
     shake
    1.24
     shaking
    1.21
     shook
    1.17
     shaken
    1.16
     Shake
    1.15
    Shake
    1.15
    shake
    1.14
     tremor
    1.09
    NameInMap
    1.04
    Activations Density 0.202%

    No Known Activations