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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2668
    Prev
    Next
    INDEX
    Explanations

    CSS style attributes related to layout and design properties

    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
    存于互联网档案馆
    -0.67
    jestel
    -0.64
     }}"></
    -0.61
     المعيارى
    -0.61
    ContentAsync
    -0.59
    __":
    -0.58
    __':
    -0.58
    ̍t
    -0.58
    IVEREF
    -0.57
    imbawa
    -0.56
    POSITIVE LOGITS
     BoxDecoration
    0.71
    CGRectMake
    0.60
    webElementXpaths
    0.60
     TextStyle
    0.60
     BorderSide
    0.58
    HttpHeaders
    0.57
    Cyfeiriadau
    0.57
    ={{
    0.57
     MonoBehaviour
    0.56
     Moodle
    0.56
    Activations Density 0.046%

    No Known Activations