© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6720
    Prev
    Next
    INDEX
    Explanations

    terms related to ethical violations in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     atom
    -0.38
     super
    -0.38
     demo
    -0.38
     portfolio
    -0.38
     pilot
    -0.37
     mission
    -0.37
     trial
    -0.35
     ed
    -0.35
     pipe
    -0.35
     works
    -0.34
    POSITIVE LOGITS
     cheating
    0.87
     للمعارف
    0.84
    MigrationBuilder
    0.82
     ब्रेकडाउन
    0.82
     dishonesty
    0.80
     cheated
    0.79
     dishonest
    0.75
     fraudul
    0.73
     cheat
    0.72
     ProtoMessage
    0.72
    Activations Density 0.872%

    No Known Activations