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. 18-GEMMASCOPE-RES-16K
    6. 14594
    Prev
    Next
    INDEX
    Explanations

    connections and relationships between entities and their interactions

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

    Follows "and" or "or," referring to a list

    np_acts-logits-general · gemini-2.0-flash

    listing conjunctions with entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputModule
    -0.56
    Demografie
    -0.55
     Players
    -0.54
     Roskov
    -0.54
     ✭✭
    -0.54
    তথ্যসূত্র
    -0.53
    UserDao
    -0.53
    Népesség
    -0.52
    user
    -0.52
     InputDecoration
    -0.52
    POSITIVE LOGITS
     незавершена
    0.82
     inanimate
    0.71
     institutions
    0.70
     groups
    0.66
     animals
    0.64
     machines
    0.63
     organizations
    0.60
     machine
    0.58
     institution
    0.58
     material
    0.57
    Activations Density 0.301%

    No Known Activations