© 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. 28-GEMMASCOPE-RES-16K
    6. 4897
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or questioning of ideas and beliefs

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

    Text before "missing", "erred", "wrong", "incorrect"

    np_acts-logits-general · gemini-2.0-flash

    errors and mistakes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.46
    expose
    -0.43
     يتيمه
    -0.43
    httphttps
    -0.40
    хьтан
    -0.38
     bekas
    -0.38
     Défense
    -0.38
     Stolz
    -0.38
     zemi
    -0.38
     повіт
    -0.37
    POSITIVE LOGITS
     wrong
    1.36
     incorrect
    1.15
     misunder
    1.14
     Wrong
    1.09
     misunderstood
    1.06
     misunderstand
    1.05
     mistaken
    1.05
    wrong
    1.03
     incorrectly
    1.03
    Wrong
    1.02
    Activations Density 0.724%

    No Known Activations