© 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. 9150
    Prev
    Next
    INDEX
    Explanations

    responses and replies in various contexts

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

    a response or reply

    np_acts-logits-general · gemini-2.0-flash

    responded to

    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
    ellschaft
    -0.74
    UnknownFieldSet
    -0.69
    ⓧ
    -0.63
    AnimationsModule
    -0.63
    CppMethod
    -0.61
    NgModule
    -0.59
    ngdoc
    -0.58
    ContentAsync
    -0.57
    WebElementEntity
    -0.55
    存于互联网档案馆
    -0.55
    POSITIVE LOGITS
     queries
    0.65
    OGND
    0.62
    reportWebVitals
    0.57
     stimuli
    0.56
     threats
    0.54
    imothy
    0.53
    queries
    0.52
     actes
    0.52
     répondu
    0.52
     positively
    0.52
    Activations Density 0.151%

    No Known Activations