© 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. 12-GEMMASCOPE-RES-16K
    11. 1904
    Prev
    Next
    INDEX
    Explanations

    conditional statements and their structure in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hotel
    -0.39
    canestro
    -0.39
    NameValuePair
    -0.38
    charCodeAt
    -0.38
     hoteles
    -0.36
     transfieras
    -0.36
    ɝ
    -0.36
     féd
    -0.35
     hydrogen
    -0.35
     Esper
    -0.35
    POSITIVE LOGITS
    else
    0.56
    subpackage
    0.55
     препратки
    0.55
    脚注の使い方
    0.53
     ELSE
    0.52
    transQ
    0.52
    Otherwise
    0.52
    dafx
    0.51
    SpringRunner
    0.50
    catchError
    0.50
    Activations Density 0.057%

    No Known Activations