© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2658
    Prev
    Next
    INDEX
    Explanations

    programming constructs and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.80
     CreateTagHelper
    -0.77
    ConstraintMaker
    -0.76
     propOrder
    -0.75
     fashiola
    -0.74
    <unused79>
    -0.73
    ஡
    -0.73
    <unused47>
    -0.73
    <unused14>
    -0.73
    [@BOS@]
    -0.72
    POSITIVE LOGITS
    ManyToOne
    0.32
    ‘
    0.30
     I
    0.29
     Co
    0.29
     published
    0.29
     His
    0.29
    @[+][
    0.28
    exception
    0.28
     Ro
    0.28
     written
    0.27
    Activations Density 0.415%

    No Known Activations