© 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. 11299
    Prev
    Next
    INDEX
    Explanations

    negations and comparisons in statements

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

    contrasts and negations, particularly structures presenting alternatives like "not...but" or "rather than" comparisons.

    oai_token-act-pair · claude-4-5-haikuTriggered by @areeb0102
    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
     pleaſure
    -0.48
     Diſ
    -0.43
     houſe
    -0.41
     Majefty
    -0.40
     Reſ
    -0.39
    UnusedPrivate
    -0.38
     ſt
    -0.38
    Datuak
    -0.38
     uſed
    -0.37
    Pranala
    -0.36
    POSITIVE LOGITS
    而非
    0.71
    而不是
    0.67
     rather
    0.65
     anstatt
    0.58
    rather
    0.56
    Rather
    0.54
     Rather
    0.52
     piuttosto
    0.51
     statt
    0.50
     &___
    0.50
    Activations Density 0.377%

    No Known Activations