© 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. 18-GEMMASCOPE-RES-16K
    11. 6409
    Prev
    Next
    INDEX
    Explanations

    file handling and directory management references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File system operations/errors

    np_acts-logits-general · gemini-2.0-flash

    file or directory not found

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     purpoſe
    -0.67
     Monfieur
    -0.64
    niająca
    -0.61
     leaſt
    -0.58
     poffible
    -0.57
     enfans
    -0.56
     reaſon
    -0.55
     ſeveral
    -0.55
     ſuch
    -0.54
     ſen
    -0.54
    POSITIVE LOGITS
     has
    1.02
     is
    0.93
     was
    0.83
     not
    0.80
     found
    0.77
     failed
    0.74
     changed
    0.73
     cannot
    0.71
     telah
    0.70
     gone
    0.68
    Activations Density 0.383%

    No Known Activations