© 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. 5321
    Prev
    Next
    INDEX
    Explanations

    the beginning of significant sections or markers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Huh
    -0.46
    con
    -0.43
     con
    -0.42
     secondo
    -0.42
    Het
    -0.42
     «
    -0.42
    看上去
    -0.42
    рованного
    -0.41
    翼
    -0.40
     tắm
    -0.40
    POSITIVE LOGITS
    enumi
    8.42
    enumii
    4.92
     CreateTagHelper
    1.37
    ValueStyle
    1.36
    findpost
    1.31
    Geplaatst
    1.30
    BeginContext
    1.30
     MainAxisSize
    1.30
    \{\\
    1.29
    CloseOperation
    1.26
    Activations Density 0.003%

    No Known Activations