© 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. 30-GEMMASCOPE-RES-16K
    11. 13083
    Prev
    Next
    INDEX
    Explanations

    negations or negative sentiments expressed in various contexts

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

    Comes after "not"

    np_acts-logits-general · gemini-2.0-flash

    not exactly, doesn't give, not content, not eager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.54
     iprot
    -0.43
    AnimationsModule
    -0.42
    ftagPool
    -0.41
     almost
    -0.41
    almost
    -0.41
    GHIJKLM
    -0.40
     useRef
    -0.39
    GOTREF
    -0.39
     occasionally
    -0.39
    POSITIVE LOGITS
    ApiModelProperty
    0.52
     conducive
    0.52
    subpackage
    0.50
     guère
    0.50
     kasarigan
    0.49
     surla
    0.48
     ejemplar
    0.47
    enderror
    0.46
    astéro
    0.46
    rovna
    0.46
    Activations Density 0.276%

    No Known Activations