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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4357
    Prev
    Next
    INDEX
    Explanations

    HTML header elements and mathematical notations

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

    Text followed by a bracketed citation

    np_acts-logits-general · gemini-2.0-flash

    bracketed citations and references

    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
    ing
    -1.16
     AdapterView
    -0.79
    Pere
    -0.76
    WindowConstants
    -0.74
    Parameteri
    -0.71
    tzmann
    -0.70
    en
    -0.68
    KeySpec
    -0.68
    ING
    -0.68
    Билгалдахарш
    -0.67
    POSITIVE LOGITS
    <h1>
    1.19
    ities
    0.84
    odeon
    0.74
    ization
    0.71
    ability
    0.70
    odor
    0.67
    ../../../
    0.66
     HomeComponent
    0.65
    sions
    0.65
    iences
    0.65
    Activations Density 0.210%

    No Known Activations