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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 15855
    Prev
    Next
    INDEX
    Explanations

    instances of images and image-related tags in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.77
    ripple
    -0.58
    atelle
    -0.57
    GroupLayout
    -0.57
    EndInit
    -0.57
    thenReturn
    -0.56
     verloren
    -0.53
    menjadi
    -0.51
     Furman
    -0.51
    numerusform
    -0.51
    POSITIVE LOGITS
    Image
    1.60
    img
    1.54
     Image
    1.51
    image
    1.42
     image
    1.30
     IMAGE
    1.24
    IMAGE
    1.21
     Images
    1.17
    IMG
    1.17
    ImageView
    1.17
    Activations Density 0.045%

    No Known Activations