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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 12912
    Prev
    Next
    INDEX
    Explanations

    phrases related to food preparation, particularly those involving potatoes

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

    Referring to potatoes

    np_acts-logits-general · gemini-2.0-flash

    potato and tubers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     frame
    -0.65
     Frame
    -0.63
     Frames
    -0.62
     FRAME
    -0.60
    Frames
    -0.58
    
    -0.56
     Henson
    -0.56
     frames
    -0.56
     mergeFrom
    -0.56
    frame
    -0.56
    POSITIVE LOGITS
     potato
    1.36
     potatoes
    1.31
     Potato
    1.24
     tubers
    1.21
     Potatoes
    1.12
    Potato
    1.10
    potato
    1.07
     Idaho
    1.05
     tuber
    1.05
    Potatoes
    1.02
    Activations Density 0.178%

    No Known Activations