© 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. 22-GEMMASCOPE-RES-16K
    11. 12585
    Prev
    Next
    INDEX
    Explanations

    HTML header tags that indicate important sections in the document

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

    HTML heading tags (h2, h3, h4)

    np_acts-logits-general · gemini-2.0-flash

    old english formal language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -0.80
     b
    -0.80
     or
    -0.78
     de
    -0.77
     to
    -0.76
     co
    -0.75
     col
    -0.75
     ir
    -0.75
     d
    -0.74
     p
    -0.74
    POSITIVE LOGITS
     itſelf
    1.54
     Houſe
    1.41
     myſelf
    1.40
     Diſ
    1.38
     Majefty
    1.37
     pleaſure
    1.37
     greateſt
    1.37
     juſt
    1.33
     Reſ
    1.33
     ſche
    1.32
    Activations Density 0.036%

    No Known Activations