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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11984
    Prev
    Next
    INDEX
    Explanations

    references to separate entities or distinct occurrences

    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
    ichord
    -0.66
    ItemLayout
    -0.65
    DockStyle
    -0.64
     dezelve
    -0.61
    PhysRev
    -0.61
     ainfi
    -0.60
    帖最后由
    -0.60
    生平
    -0.59
     uſ
    -0.59
     asisti
    -0.59
    POSITIVE LOGITS
     separate
    1.55
    Separate
    1.43
    separate
    1.42
     Separate
    1.36
     SEPAR
    1.15
     seperate
    1.15
     terpisah
    1.13
     separately
    1.12
     separat
    1.06
     separado
    1.05
    Activations Density 0.343%

    No Known Activations