© 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. 11-GEMMASCOPE-RES-16K
    11. 2452
    Prev
    Next
    INDEX
    Explanations

    various forms of assessment tools and methodologies in research contexts

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

    references to specific technical resources or instruments being introduced (often with “this/the”) and then described or characterized.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.84
    OGND
    -0.76
    TypedDataSet
    -0.75
     дописавши
    -0.72
    bootstrapcdn
    -0.70
    WriteTagHelper
    -0.69
    LookAnd
    -0.64
     فريبيس
    -0.64
     GenerationType
    -0.62
     typelib
    -0.61
    POSITIVE LOGITS
     includes
    0.72
     is
    0.72
     involves
    0.72
     consists
    0.71
     include
    0.65
     encompasses
    0.65
     also
    0.64
     comprises
    0.62
     was
    0.60
     may
    0.60
    Activations Density 0.779%

    No Known Activations