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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1590
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of doubt or uncertainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.79
     houſe
    -0.67
     preſent
    -0.58
     purpoſe
    -0.56
     ſmall
    -0.56
     raiſ
    -0.55
     ſtate
    -0.54
     faſt
    -0.54
    ValueStyle
    -0.54
     AssemblyTitle
    -0.52
    POSITIVE LOGITS
     Does
    0.63
     does
    0.61
     DID
    0.58
    does
    0.58
    Does
    0.57
     DOES
    0.56
     need
    0.55
    DOES
    0.54
     did
    0.53
     give
    0.52
    Activations Density 0.156%

    No Known Activations