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. 14048
    Prev
    Next
    INDEX
    Explanations

    mention of action figures and related merchandise

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

    Action figures and dolls

    np_acts-logits-general · gemini-2.0-flash

    action figures and dolls

    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
     Scritto
    -0.55
    EDEFAULT
    -0.52
     Bioinformatics
    -0.52
    igslist
    -0.51
    izr
    -0.51
    guous
    -0.51
     énergé
    -0.50
     propOrder
    -0.50
     OpenStreetMap
    -0.49
    熬
    -0.49
    POSITIVE LOGITS
     figures
    1.24
     figure
    1.19
     toy
    1.14
     figurines
    1.13
     toys
    1.12
     figurine
    1.08
     Figures
    1.07
     collectible
    1.06
    figures
    1.04
     dolls
    1.03
    Activations Density 0.129%

    No Known Activations