© 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. 15-GEMMASCOPE-RES-16K
    11. 4888
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions or areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.79
     Majefty
    -0.79
     Diſ
    -0.77
     Houſe
    -0.76
    neſs
    -0.74
     pleaſure
    -0.73
     neceffary
    -0.71
     poffible
    -0.70
     itſelf
    -0.70
     Anſ
    -0.70
    POSITIVE LOGITS
    :✨
    0.53
    役
    0.49
    EDEFAULT
    0.49
    aarrggbb
    0.49
    eradish
    0.47
    hoeddwyd
    0.46
     '\\;'
    0.46
     ***!
    0.45
    HostException
    0.44
    Chham
    0.44
    Activations Density 0.286%

    No Known Activations