© 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. 28-GEMMASCOPE-RES-16K
    11. 8106
    Prev
    Next
    INDEX
    Explanations

    phrases expressing misconceptions and clarifications regarding ownership and historical contexts

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

    Contradiction or qualification

    np_acts-logits-general · gemini-2.0-flash

    says nothing

    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
     EconPapers
    -0.50
     utafitiHapana
    -0.38
    IntoConstraints
    -0.33
    propor
    -0.32
    Diwedd
    -0.32
    brille
    -0.31
     Drag
    -0.31
     Peter
    -0.31
     Lieber
    -0.31
    sorting
    -0.31
    POSITIVE LOGITS
     nonetheless
    0.63
     betyr
    0.63
     betekent
    0.60
     nevertheless
    0.59
     doesn
    0.59
     betyder
    0.58
    並不
    0.58
     notwithstanding
    0.53
     doesnt
    0.53
     does
    0.52
    Activations Density 0.287%

    No Known Activations