© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5815
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of limitation or inability

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

    Followed by a negated word ("not", "without", "no")

    np_acts-logits-general · gemini-2.0-flash

    not without no cannot

    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
     ſta
    -0.60
     ſou
    -0.58
     myſelf
    -0.57
     Monfieur
    -0.57
     ſch
    -0.56
     ſche
    -0.56
     preſent
    -0.56
     Diſ
    -0.55
     Inſ
    -0.55
     ſind
    -0.55
    POSITIVE LOGITS
    UrlResolution
    0.35
     any
    0.31
    UseVisualStyle
    0.30
    cat
    0.30
     anything
    0.29
     long
    0.28
    ỡng
    0.27
    acy
    0.27
    urement
    0.27
     mention
    0.26
    Activations Density 0.032%

    No Known Activations