© 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. 31-GEMMASCOPE-RES-16K
    11. 11671
    Prev
    Next
    INDEX
    Explanations

    Java programming constructs, particularly object creation and method invocation patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    variable assignment operations using the equals sign in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumii
    -0.57
     للمعارف
    -0.52
     يتيمه
    -0.52
    AddHtmlAttribute
    -0.45
    RTCF
    -0.44
     препратки
    -0.44
     utafitiHapana
    -0.42
     Signalez
    -0.41
    AndEndTag
    -0.41
    ropractic
    -0.41
    POSITIVE LOGITS
     nothing
    2.00
     none
    1.90
     None
    1.78
    None
    1.73
    nothing
    1.70
    none
    1.67
     NOTHING
    1.63
    Nothing
    1.62
     Nothing
    1.59
     NONE
    1.53
    Activations Density 1.820%

    No Known Activations