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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6633
    Prev
    Next
    INDEX
    Explanations

    terms related to parasitic infections and related immune responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VolleyError
    -0.38
    RefreshLayout
    -0.36
    うち
    -0.36
    jobb
    -0.36
    NavigationView
    -0.35
     fédé
    -0.34
    CloseOperation
    -0.33
    PyExc
    -0.33
    ViewComponent
    -0.32
    MockMvc
    -0.32
    POSITIVE LOGITS
     parasites
    0.68
     parasite
    0.68
     parasitic
    0.67
    исленность
    0.61
     Paras
    0.58
    paras
    0.58
    寄生
    0.57
    asitic
    0.57
    :✨
    0.53
    Paras
    0.53
    Activations Density 1.640%

    No Known Activations