© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13161
    Prev
    Next
    INDEX
    Explanations

    negations and differentiations in statements

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

    contrasting or negating statements using words like "not," "wasn't," and "can't."

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.69
    AddTagHelper
    -0.69
    ſelves
    -0.63
     Monfieur
    -0.59
     myſelf
    -0.59
     auffi
    -0.58
    NameInMap
    -0.57
    帖最后由
    -0.57
     ſever
    -0.56
     pleaſure
    -0.55
    POSITIVE LOGITS
    唯一
    1.76
     един
    1.60
    唯一的
    1.54
     única
    1.41
     único
    1.41
     sole
    1.38
     einzige
    1.38
     únicos
    1.33
     jedin
    1.32
     eneste
    1.31
    Activations Density 0.475%

    No Known Activations