© 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. 33-GEMMASCOPE-RES-16K
    11. 372
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical and logical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.59
    LookAnd
    -0.57
    principalColumn
    -0.55
    MessageOf
    -0.53
    pecabe
    -0.50
     noDo
    -0.50
    లాలు
    -0.49
    󠁴
    -0.49
    enterOuterAlt
    -0.47
     pelatih
    -0.47
    POSITIVE LOGITS
     للمعارف
    0.69
     esternos
    0.50
     uParam
    0.45
     iParam
    0.45
     bParam
    0.44
    permum
    0.41
    iParam
    0.41
     ligiloj
    0.40
     localObject
    0.40
    RegressionTest
    0.39
    Activations Density 0.445%

    No Known Activations