© 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. 25-GEMMASCOPE-RES-16K
    11. 16140
    Prev
    Next
    INDEX
    Explanations

    negations and phrases related to requirements or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conſ
    -0.53
    OGND
    -0.52
     Reſ
    -0.51
     <<<<<<<<<<<<<<
    -0.49
    újo
    -0.49
    delwed
    -0.48
     intStringLen
    -0.48
     насељу
    -0.47
     TextAppearance
    -0.47
     faſt
    -0.47
    POSITIVE LOGITS
     neither
    0.45
     Neither
    0.40
    そんなに
    0.39
     żad
    0.39
     any
    0.38
    Neither
    0.37
    scryfall
    0.37
    BindingResult
    0.36
    PostBack
    0.36
     clearColor
    0.36
    Activations Density 0.283%

    No Known Activations