© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3293
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and conjunctions linking phrases or clauses together

    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
     mijne
    -0.48
     Sünde
    -0.45
     avoient
    -0.45
     étoit
    -0.43
     peuples
    -0.42
    InputTagHelper
    -0.42
     rép
    -0.42
     infierno
    -0.41
     ſtand
    -0.41
    mentação
    -0.41
    POSITIVE LOGITS
    帖最后由
    0.58
    Біографія
    0.49
    gemeester
    0.47
     Lemon
    0.47
    ❋
    0.46
    libft
    0.46
     kasarigan
    0.46
    Notae
    0.45
    ссора
    0.44
     Messrs
    0.44
    Activations Density 0.209%

    No Known Activations