© 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. 27-GEMMASCOPE-RES-16K
    6. 8882
    Prev
    Next
    INDEX
    Explanations

    negations and phrases indicating the absence or exclusion of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     неза
    -0.33
    ss
    -0.32
    1
    -0.31
    合
    -0.31
    App
    -0.31
    Drawable
    -0.30
    CNP
    -0.29
    Call
    -0.29
    Catch
    -0.29
    2
    -0.28
    POSITIVE LOGITS
     necessarily
    0.78
    parsedMessage
    0.68
     estekak
    0.68
    StoryboardSegue
    0.68
    IntoConstraints
    0.68
     necessariamente
    0.68
     चीज़ों
    0.67
     ProtoMessage
    0.66
    necessarily
    0.65
    MigrationBuilder
    0.65
    Activations Density 0.936%

    No Known Activations