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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 115
    Prev
    Next
    INDEX
    Explanations

    syntactic structures or programming constructs related to definitions and type declarations

    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
     betweenstory
    -0.73
     <<<<<<<<<<<<<<
    -0.68
    niſſe
    -0.67
     snippetHide
    -0.67
    migrationBuilder
    -0.65
    RegressionTest
    -0.63
    UserScript
    -0.62
    fromnode
    -0.61
     CanadaChoose
    -0.61
    GEBURTSDATUM
    -0.60
    POSITIVE LOGITS
     speed
    0.59
     price
    0.54
     density
    0.49
     height
    0.49
     size
    0.48
     vitesse
    0.47
     fréquence
    0.47
     frequency
    0.46
     strength
    0.46
     income
    0.45
    Activations Density 0.602%

    No Known Activations