© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12005
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betreft
    -0.53
     فريبيس
    -0.52
    醐
    -0.52
    NOPQRST
    -0.51
    BorderFactory
    -0.48
     Савезне
    -0.44
    ❷
    -0.43
    aarrggbb
    -0.42
    ագրություններ
    -0.42
    ToUser
    -0.40
    POSITIVE LOGITS
    SequentialGroup
    1.00
    InstrumentedTest
    0.77
    سطس
    0.77
     getRule
    0.74
    AddHtmlAttribute
    0.72
    findpost
    0.66
    VIAF
    0.63
    WillAppear
    0.61
    eventbus
    0.61
    AccessorTable
    0.59
    Activations Density 0.366%

    No Known Activations