Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 11598
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism and analysis of visual elements in artistic or media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.82
     myſelf
    -0.81
     للاسماء
    -0.80
     themſelves
    -0.77
     poffible
    -0.76
     himſelf
    -0.75
    featureID
    -0.75
     ſtate
    -0.75
     utafitiHapana
    -0.74
     Monfieur
    -0.72
    POSITIVE LOGITS
    GHIJKLM
    0.52
    DockStyle
    0.51
    openzeppelin
    0.45
    minecraft
    0.43
    Frm
    0.42
    ohar
    0.41
    iyaki
    0.41
     spiller
    0.40
    كار
    0.40
    mf
    0.39
    Activations Density 0.594%

    No Known Activations