© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 473
    Prev
    Next
    INDEX
    Explanations

    references to specific media titles and character names from a particular genre

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

    Appears in film names or non-English

    np_acts-logits-general · gemini-2.0-flash

    words from various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
     ویکی‌پدیای
    -0.64
     AssemblyTitle
    -0.52
    yntaxException
    -0.51
     InputDecoration
    -0.47
    Vidite
    -0.46
     展板
    -0.45
     setUsername
    -0.45
    LabelTagHelper
    -0.44
    +#+
    -0.43
    󠁬
    -0.43
    POSITIVE LOGITS
     ffilmiau
    0.44
    pragma
    0.44
    Enllaces
    0.40
     دیکھیے
    0.38
    SpringRunner
    0.37
     rhestr
    0.36
    ıştı
    0.34
     verhält
    0.34
     luyện
    0.33
     Sumer
    0.33
    Activations Density 0.181%

    No Known Activations