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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 2417
    Prev
    Next
    INDEX
    Explanations

    phrases indicating requests or interactions related to scheduling and business needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    だが
    -0.84
    だったが
    -0.77
    AddTagHelper
    -0.76
    であるが
    -0.75
    ようだ
    -0.72
    ")->
    -0.66
    protoimpl
    -0.65
    이다
    -0.65
     يتيمه
    -0.65
    曖昧さ回避
    -0.64
    POSITIVE LOGITS
     your
    4.30
    your
    3.31
    Your
    2.60
     Your
    2.43
     YOUR
    2.35
    YOUR
    2.31
    你的
    2.24
     votre
    2.20
    您的
    2.11
     yours
    2.04
    Activations Density 1.628%

    No Known Activations