© 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. 2-GEMMASCOPE-RES-16K
    11. 2361
    Prev
    Next
    INDEX
    Explanations

    various forms of punctuation and formatting marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.64
    stateProvider
    -0.63
    mapStateToProps
    -0.62
     springfox
    -0.60
     חיצוניים
    -0.59
     iNdEx
    -0.58
     zeros
    -0.55
    =#{
    -0.54
    Бахар
    -0.54
    gdx
    -0.53
    POSITIVE LOGITS
    Rhestr
    0.63
     _____
    0.61
    ______
    0.60
     propOrder
    0.56
    _____
    0.56
     ______
    0.56
     Meksiku
    0.55
     ____
    0.54
     _______
    0.54
    _.
    0.52
    Activations Density 0.230%

    No Known Activations