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. 24-GEMMASCOPE-RES-16K
    6. 12782
    Prev
    Next
    INDEX
    Explanations

    HTML class and ID attributes in the document

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

    HTML/code class attributes

    np_acts-logits-general · gemini-2.0-flash

    HTML class="

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.69
    Personensuche
    -0.61
     Croce
    -0.60
     استنادى
    -0.55
    تقاوى
    -0.54
     MIME
    -0.54
     allegro
    -0.54
     endblock
    -0.54
    참고
    -0.53
     techniczne
    -0.52
    POSITIVE LOGITS
    classnames
    0.58
    ilever
    0.53
     Bam
    0.49
    alors
    0.48
     Propel
    0.48
     něj
    0.47
     classname
    0.47
     Kelas
    0.46
    ftagPool
    0.44
     renforcé
    0.44
    Activations Density 0.052%

    No Known Activations