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. 23-GEMMASCOPE-RES-16K
    6. 12351
    Prev
    Next
    INDEX
    Explanations

    terms related to "scandal" or similar concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.81
     المعيارى
    -0.70
    httphttps
    -0.68
    DispatchToProps
    -0.67
    AccessorTable
    -0.66
     nahilalakip
    -0.64
     ویکی‌پدی
    -0.63
    __*/
    -0.61
    StoreMessageInfo
    -0.60
     pinulongan
    -0.59
    POSITIVE LOGITS
     Braga
    0.56
     Freiburg
    0.52
    ientôt
    0.49
     Rine
    0.49
    kijken
    0.49
     sc
    0.48
     Pristup
    0.47
    rouge
    0.47
     Sc
    0.47
     survie
    0.47
    Activations Density 0.114%

    No Known Activations