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. 14-GEMMASCOPE-RES-16K
    6. 2982
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hang" and its variants related to physical or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arakhand
    -0.78
    MemoryWarning
    -0.75
    phorbia
    -0.74
     propellant
    -0.73
    propTypes
    -0.70
     propOrder
    -0.70
     Zahn
    -0.68
     sqlSession
    -0.67
    Життєпис
    -0.66
    CrossRef
    -0.66
    POSITIVE LOGITS
     Hang
    1.49
     HANG
    1.42
     hang
    1.30
     hung
    1.29
    Hang
    1.22
     hangs
    1.21
     hanging
    1.19
     Attachment
    1.10
     hanger
    1.10
    hang
    1.07
    Activations Density 0.400%

    No Known Activations