© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 9404
    Prev
    Next
    INDEX
    Explanations

    references to middle-class and mid-tier topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.79
     uVar
    -0.77
     françaises
    -0.72
    المكان
    -0.70
    [])
    -0.69
     polvere
    -0.68
    indeer
    -0.66
    ']?>
    -0.66
    enoord
    -0.65
    таратура
    -0.65
    POSITIVE LOGITS
     Middel
    1.34
     MID
    1.24
     Mid
    1.12
    Mid
    1.08
     MIDDLE
    1.06
     mid
    1.02
     Middle
    0.99
     Middleware
    0.97
    Middle
    0.94
     middle
    0.94
    Activations Density 0.123%

    No Known Activations