© 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. 1-GEMMASCOPE-RES-16K
    11. 2258
    Prev
    Next
    INDEX
    Explanations

    introductory phrases that indicate a description or explanation of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleable
    -0.60
     يتيمه
    -0.59
     yonder
    -0.57
     miniaturka
    -0.55
     CURIAM
    -0.54
    +#+#
    -0.53
    ésult
    -0.51
    phosa
    -0.51
     StringTokenizer
    -0.51
    himovic
    -0.50
    POSITIVE LOGITS
     Being
    0.85
     Get
    0.77
     About
    0.77
     Been
    0.75
     Your
    0.75
    Being
    0.72
    About
    0.69
     Another
    0.65
    Been
    0.65
     Having
    0.64
    Activations Density 0.322%

    No Known Activations