© 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. 4314
    Prev
    Next
    INDEX
    Explanations

    terms related to matching, comparing, and imitating

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

    replicating or imitating

    np_acts-logits-general · gemini-2.0-flash

    mimic, replicate, copy, emulate

    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
    ModelAdmin
    -0.40
    TagMode
    -0.38
     ComVisible
    -0.38
    anasia
    -0.35
     intermédiaire
    -0.34
     Dimensiones
    -0.33
     tunggal
    -0.33
     niks
    -0.30
     defaultstate
    -0.30
    hermosa
    -0.30
    POSITIVE LOGITS
    TRAILING
    0.55
    enumii
    0.52
     emulate
    0.52
    arraycopy
    0.49
     replicate
    0.48
    AlterField
    0.48
     imitate
    0.47
    featureID
    0.47
    Imit
    0.47
    RepeatedField
    0.47
    Activations Density 0.408%

    No Known Activations