© 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. 25-GEMMASCOPE-RES-16K
    6. 10742
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic writing

    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
    UserScript
    -0.64
    sizeCache
    -0.64
    AlterField
    -0.60
     Darum
    -0.51
    Viungo
    -0.51
    writerow
    -0.51
    OGND
    -0.50
     aver
    -0.49
    StoryboardSegue
    -0.49
    swire
    -0.49
    POSITIVE LOGITS
     dot
    0.59
    ⋅
    0.56
    .
    0.54
    CloseOperation
    0.52
    ंदीखरीदारी
    0.49
    cdot
    0.49
    DOT
    0.48
     ͡°
    0.48
    \.
    0.47
     ciné
    0.46
    Activations Density 0.870%

    No Known Activations