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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6842
    Prev
    Next
    INDEX
    Explanations

    references to colloidal beads and related materials in scientific contexts

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

    "bead" or "beads."

    np_acts-logits-general · gemini-2.0-flash

    beads and grains

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    MethodManager
    -0.62
    ChildScrollView
    -0.53
     leaſt
    -0.51
     trí
    -0.48
    rungsseite
    -0.46
    SequentialGroup
    -0.45
    Хьажоргаш
    -0.44
     ModelExpression
    -0.44
     pleaſure
    -0.43
     Houſe
    -0.42
    POSITIVE LOGITS
     beads
    1.06
     bead
    1.04
     Beads
    0.94
    Bead
    0.93
     Bead
    0.93
    bead
    0.87
    beads
    0.84
     pellets
    0.80
     pearls
    0.77
     pellet
    0.76
    Activations Density 0.800%

    No Known Activations