© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11601
    Prev
    Next
    INDEX
    Explanations

    words related to images and visual media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.51
     myſelf
    -1.48
     purpoſe
    -1.41
     pleaſure
    -1.40
     raiſ
    -1.39
     Efq
    -1.38
     Reſ
    -1.36
     houſe
    -1.36
     Majefty
    -1.33
     Monfieur
    -1.31
    POSITIVE LOGITS
     ir
    0.61
     did
    0.60
     bei
    0.54
     d
    0.54
     
    0.53
     g
    0.52
     p
    0.51
     l
    0.49
     di
    0.48
     at
    0.48
    Activations Density 0.066%

    No Known Activations