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. 16-GEMMASCOPE-RES-16K
    6. 2984
    Prev
    Next
    INDEX
    Explanations

    verbs and expressions related to movement or flowing downwards

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

    Movement (down, up, running, descending, over)

    np_acts-logits-general · gemini-2.0-flash

    down, up, running, along

    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
    tyard
    -0.65
     tubercle
    -0.60
    awtextra
    -0.57
    icrous
    -0.57
    ächtig
    -0.57
    حياته
    -0.56
     للاسماء
    -0.56
     intptr
    -0.56
     Plutarch
    -0.56
    taur
    -0.56
    POSITIVE LOGITS
    Бахар
    0.63
     lines
    0.61
    LookAnd
    0.61
     the
    0.57
    weg
    0.57
     line
    0.54
    XmlAccessorType
    0.52
     فہرست
    0.52
     along
    0.50
     through
    0.50
    Activations Density 0.144%

    No Known Activations