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. 15-GEMMASCOPE-RES-16K
    6. 2282
    Prev
    Next
    INDEX
    Explanations

    concepts related to beliefs and judgments about differences among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jellemző
    -0.58
     répondre
    -0.57
    ganggu
    -0.56
     podríamos
    -0.55
     natuurlijk
    -0.55
    tamment
    -0.54
     quelcon
    -0.54
     tentunya
    -0.52
     răsp
    -0.52
     främ
    -0.52
    POSITIVE LOGITS
     allAfrica
    0.74
    MessageOf
    0.69
    StoryboardSegue
    0.65
    Personensuche
    0.65
     utafitiHapana
    0.64
    WithIOException
    0.63
    jewództ
    0.63
    GEBURTSDATUM
    0.61
     OFDb
    0.61
    BufferException
    0.60
    Activations Density 0.238%

    No Known Activations