© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5074
    Prev
    Next
    INDEX
    Explanations

    descriptions of semiconductor devices and their manufacturing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.53
    ObjectContext
    -0.52
    rupal
    -0.51
    penup
    -0.49
     kiệm
    -0.46
     BytesLike
    -0.45
     geografic
    -0.44
    ju
    -0.44
    MENAFN
    -0.43
     població
    -0.42
    POSITIVE LOGITS
     OMITBAD
    0.73
    KURZBESCHREIBUNG
    0.69
     AssemblyCulture
    0.69
     كومونز
    0.65
    RegressionTest
    0.63
    ſelf
    0.62
    ikistan
    0.62
     pungkas
    0.61
     fubject
    0.60
     resourceCulture
    0.60
    Activations Density 0.870%

    No Known Activations