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. 20-GEMMASCOPE-RES-16K
    6. 4887
    Prev
    Next
    INDEX
    Explanations

    references to the term "Tam" and its variations

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

    Following the word "Tam"

    np_acts-logits-general · gemini-2.0-flash

    words starting with Tam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arder
    -0.55
    closePath
    -0.53
    wój
    -0.52
    glers
    -0.51
    SubCategory
    -0.51
    ueger
    -0.49
    Africa
    -0.48
    anthene
    -0.47
    graphy
    -0.47
    effetto
    -0.47
    POSITIVE LOGITS
    Tam
    0.79
     Tam
    0.72
    JspWriter
    0.69
     pinulongan
    0.66
     createSlice
    0.66
     dimming
    0.64
    SerializeField
    0.63
     referenties
    0.63
     obstante
    0.62
    ]=>
    0.61
    Activations Density 0.190%

    No Known Activations