© 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. 0-GEMMASCOPE-RES-16K
    11. 14950
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms and statistical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iffance
    -0.87
     sánchez
    -0.86
     lópez
    -0.80
     rodríguez
    -0.79
     gonzález
    -0.78
    avelength
    -0.72
     meriva
    -0.72
    iterranée
    -0.69
     abbildung
    -0.68
     kapture
    -0.68
    POSITIVE LOGITS
    <bos>
    1.43
    nip
    0.73
    cyc
    0.73
    butt
    0.71
    orb
    0.70
    luc
    0.69
    hob
    0.69
    imm
    0.69
    fork
    0.68
    Berg
    0.68
    Activations Density 6.444%

    No Known Activations