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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 10134
    Prev
    Next
    INDEX
    Explanations

    boolean values and related expressions in code

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

    "false" boolean values

    np_acts-logits-general · gemini-2.0-flash

    boolean false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tabular
    -0.58
     AssemblyTitle
    -0.58
    vistar
    -0.57
    ingway
    -0.55
     سكانية
    -0.54
    Viking
    -0.54
    HAT
    -0.53
    Avi
    -0.53
    tap
    -0.53
    Pik
    -0.53
    POSITIVE LOGITS
     False
    0.92
     false
    0.88
    False
    0.86
    false
    0.84
    stdbool
    0.83
     FALSE
    0.79
    FALSE
    0.72
     falsos
    0.66
     falsa
    0.65
     fausse
    0.65
    Activations Density 0.076%

    No Known Activations