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. 4438
    Prev
    Next
    INDEX
    Explanations

    financial and grant-related content in research-related texts

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

    Numeric identifiers (patent/agreement numbers)

    np_acts-logits-general · gemini-2.0-flash

    patent numbers or IDs

    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
     milliers
    -0.47
    SPATH
    -0.47
     centaines
    -0.44
     hundred
    -0.44
    ReusableCell
    -0.44
     aéro
    -0.44
     bellezza
    -0.43
     îna
    -0.42
     spé
    -0.42
    UVWXYZ
    -0.41
    POSITIVE LOGITS
    djangoproject
    0.69
     calendriers
    0.68
    CodeAttribute
    0.67
    atzung
    0.66
    openqa
    0.66
     CreateTagHelper
    0.65
    netbeans
    0.63
    bollah
    0.62
    Дереккөздер
    0.60
     للمعارف
    0.59
    Activations Density 0.763%

    No Known Activations