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. 16-GEMMASCOPE-RES-16K
    6. 13176
    Prev
    Next
    INDEX
    Explanations

    food items and dishes, particularly focusing on various types of burgers and breakfast items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DllImport
    -0.65
     hinweg
    -0.59
    ocally
    -0.58
    ousands
    -0.56
    </caption>
    -0.55
    olische
    -0.54
    endphp
    -0.54
    DebuggerNonUser
    -0.53
    ändig
    -0.53
     invokingState
    -0.52
    POSITIVE LOGITS
     casserole
    0.60
    ReusableCell
    0.60
     <<<<<<<<<<<<<<
    0.59
     salads
    0.57
     recipe
    0.57
    wiches
    0.55
     heiress
    0.55
     sandwiches
    0.55
     maker
    0.55
     Casserole
    0.54
    Activations Density 0.150%

    No Known Activations