© 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. 4-GEMMASCOPE-RES-16K
    11. 1085
    Prev
    Next
    INDEX
    Explanations

    the presence of initial markers or indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scénario
    -0.68
     Италијани
    -0.59
    elemField
    -0.56
    phosa
    -0.56
     tartalomajánló
    -0.56
    SerializedName
    -0.54
    bkz
    -0.53
    ptonshire
    -0.53
    RegressionTest
    -0.53
    frain
    -0.53
    POSITIVE LOGITS
    ViewFeatures
    0.79
     CreateTagHelper
    0.72
    tagHelperRunner
    0.62
    KommentareTeilen
    0.61
    存于互联网档案馆
    0.59
     שוליים
    0.58
     Normdatei
    0.55
    GeneratedValue
    0.55
    AddTagHelper
    0.54
    IntoConstraints
    0.52
    Activations Density 0.026%

    No Known Activations