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. 9034
    Prev
    Next
    INDEX
    Explanations

    interrogative phrases related to how individuals perceive their experiences and feelings

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

    Questions involving "how" or "where"

    np_acts-logits-general · gemini-2.0-flash

    how [pronoun] [verb]

    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
    there
    -0.47
     there
    -0.45
    [
    -0.43
    There
    -0.42
     einige
    -0.42
     nekaj
    -0.41
     ain
    -0.41
     suficiente
    -0.40
    isset
    -0.40
     mavi
    -0.40
    POSITIVE LOGITS
    SharedDtor
    1.03
    Aiheesta
    0.92
    RTLD
    0.89
    djangoproject
    0.87
    脚注の使い方
    0.85
     Roskov
    0.85
    webElementXpaths
    0.84
     ujednoznacz
    0.81
     BoxFit
    0.81
     怎样
    0.81
    Activations Density 0.143%

    No Known Activations