Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 4515
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zugehen
    -0.72
     dõi
    -0.69
     RoHS
    -0.64
    betical
    -0.63
    blonde
    -0.63
     Rabat
    -0.62
    mädchen
    -0.61
     Alek
    -0.60
    trivial
    -0.59
     Corbett
    -0.59
    POSITIVE LOGITS
     experiences
    1.74
     experience
    1.73
     Experiences
    1.64
     Experience
    1.58
    Experience
    1.53
    EXPERIENCE
    1.53
    experience
    1.50
     experien
    1.49
     EXPERIENCE
    1.49
    experiences
    1.46
    Activations Density 0.049%

    No Known Activations