© 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. 20-GEMMASCOPE-RES-16K
    11. 3101
    Prev
    Next
    INDEX
    Explanations

    sequences in programming contexts involving conditionals and function calls

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

    coding and programming-related terms and actions like "run", "try", "code", "I", "when", etc.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſtre
    -0.45
    วะ
    -0.43
     kasarigan
    -0.42
    oa̍t
    -0.42
     pleaſure
    -0.42
     fhort
    -0.40
     intStringLen
    -0.40
    Dosage
    -0.38
     للمعارف
    -0.37
    rrggbb
    -0.37
    POSITIVE LOGITS
    みると
    0.43
    ifflin
    0.43
    ลอง
    0.42
     pró
    0.41
    AppMethodBeat
    0.41
    appé
    0.40
    ってみ
    0.39
    Compared
    0.39
     ब्रेकडाउन
    0.39
    してみると
    0.38
    Activations Density 0.522%

    No Known Activations