© 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. 21-GEMMASCOPE-RES-16K
    11. 4448
    Prev
    Next
    INDEX
    Explanations

    structured mathematical elements or representations, particularly arrays and alignments in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mar
    -0.50
    VersionUID
    -0.45
     mar
    -0.43
     
    -0.43
     U
    -0.43
     MAR
    -0.42
    mar
    -0.40
     safety
    -0.40
    مزید
    -0.39
    asun
    -0.39
    POSITIVE LOGITS
    principalColumn
    0.90
     ModelExpression
    0.90
     ―――――
    0.84
    Portale
    0.76
    TypedDataSet
    0.76
    Vidite
    0.75
     eventdata
    0.75
     CreateTagHelper
    0.74
     الرياضيه
    0.72
    FunctionFlags
    0.72
    Activations Density 0.100%

    No Known Activations