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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 76
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to advisors and their roles in various contexts

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

    following "to" or "for"

    np_acts-logits-general · gemini-2.0-flash

    legal representation and clients

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     contri
    -0.60
     bezeichneter
    -0.59
     Compro
    -0.55
    }{*}{
    -0.55
    存于互联网档案馆
    -0.53
    lever
    -0.52
     Créez
    -0.50
    LANDS
    -0.50
     leves
    -0.50
     TPS
    -0.49
    POSITIVE LOGITS
     kepentingan
    0.60
     pribadi
    0.60
     clients
    0.57
     kunder
    0.55
     rivista
    0.52
     spesa
    0.52
    elemField
    0.51
     campagna
    0.51
    thien
    0.49
    стю
    0.49
    Activations Density 0.252%

    No Known Activations