© 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-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 16358
    Prev
    Next
    INDEX
    Explanations

    comparative phrases related to mathematical functions and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    AutoField
    -0.36
     doigt
    -0.34
    ETHING
    -0.33
     forget
    -0.32
    ยนต์
    -0.32
     volunteers
    -0.31
     vectorielle
    -0.31
     vektör
    -0.30
     presidenta
    -0.30
    simpleType
    -0.30
    POSITIVE LOGITS
    posedge
    0.85
    leqq
    0.65
     gynhyrchwyd
    0.64
     >=",
    0.62
    leq
    0.62
    transQ
    0.61
     <=
    0.60
    geq
    0.59
    ceq
    0.58
    <=
    0.57
    Activations Density 0.677%

    No Known Activations