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. 0-GEMMASCOPE-RES-16K
    6. 7940
    Prev
    Next
    INDEX
    Explanations

    references to emotional distress or crying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )}</
    -0.68
    Còn
    -0.66
    PasswordEncoder
    -0.66
     BorderRadius
    -0.65
     bezeichneter
    -0.64
    ftagPool
    -0.63
    ArrowToggle
    -0.62
    Jalan
    -0.62
     UIN
    -0.62
     Backward
    -0.59
    POSITIVE LOGITS
     ll
    0.70
    RLock
    0.52
    ценка
    0.48
     s
    0.47
    amling
    0.46
     da
    0.46
     pomocą
    0.46
     espuma
    0.45
    OrBuilder
    0.45
    cione
    0.44
    Activations Density 0.152%

    No Known Activations