© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 467
    Prev
    Next
    INDEX
    Explanations

    terms related to images and image processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to images or image-related terminology

    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
    UnusedPrivate
    -1.07
     @"/
    -0.88
    />";
    -0.79
    IsPostBack
    -0.76
     >=",
    -0.75
     paroisse
    -0.75
    Портал
    -0.74
    principalColumn
    -0.73
     traditionnels
    -0.73
    expandindo
    -0.73
    POSITIVE LOGITS
     images
    2.17
     image
    2.14
     Image
    2.06
     Images
    1.92
     IMAGE
    1.90
    image
    1.88
    Image
    1.85
    images
    1.81
    IMAGE
    1.74
    Images
    1.72
    Activations Density 0.051%

    No Known Activations