© 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. 41-GEMMASCOPE-RES-16K
    6. 7966
    Prev
    Next
    INDEX
    Explanations

    code-related elements and structures in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.54
     MainAxisSize
    -0.53
    PyExc
    -0.48
    BufferException
    -0.44
    /**
    -0.44
    ElementException
    -0.42
    tanleria
    -0.41
    . 
    -0.41
    ########.
    -0.40
    stateProvider
    -0.40
    POSITIVE LOGITS
    2
    1.07
    3
    0.96
    two
    0.90
    1
    0.90
    4
    0.85
    5
    0.81
    Two
    0.78
    6
    0.76
    three
    0.74
    TWO
    0.74
    Activations Density 1.269%

    No Known Activations