© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7484
    Prev
    Next
    INDEX
    Explanations

    references to software components and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    간
    -0.47
    テン
    -0.47
    분
    -0.44
     jal
    -0.43
    突
    -0.43
    Bew
    -0.43
    nor
    -0.43
     fixation
    -0.42
    AMAN
    -0.42
    Begin
    -0.42
    POSITIVE LOGITS
    UseVisualStyle
    6.95
    GraphicsUnit
    1.27
     AssemblyTitle
    1.17
     propOrder
    1.16
    TabStop
    1.10
    TemporalType
    1.10
    AutoScaleMode
    1.08
    UrlResolution
    1.07
    IsContent
    1.07
    AddTagHelper
    1.06
    Activations Density 0.007%

    No Known Activations