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. 5-GEMMASCOPE-RES-16K
    6. 4238
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fetch" and its variations, indicating a focus on data retrieval processes

    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
    rekli
    -0.64
     Milner
    -0.63
    CardContent
    -0.59
     Club
    -0.59
     initialState
    -0.58
     erw
    -0.58
     råd
    -0.58
    ways
    -0.56
    shiro
    -0.56
    ض
    -0.56
    POSITIVE LOGITS
     fetch
    2.41
    fetch
    2.34
     Fetch
    2.31
     FETCH
    2.15
    Fetch
    2.07
    FETCH
    1.94
     fetching
    1.86
     fetched
    1.78
    fetching
    1.62
    Fetching
    1.59
    Activations Density 0.037%

    No Known Activations