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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15599
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the theme of bias and its impact in various contexts

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

    "in" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    in order

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protobuf
    -0.46
     prostu
    -0.45
     isso
    -0.44
     ago
    -0.44
    autogui
    -0.44
     ruedas
    -0.41
    переди
    -0.41
     Daniel
    -0.41
    balo
    -0.41
    DebuggerNonUser
    -0.41
    POSITIVE LOGITS
    GraphicsUnit
    0.85
    ValueStyle
    0.82
    tagHelperRunner
    0.78
     ways
    0.77
     itſelf
    0.72
    tvguidetime
    0.72
    AccessorTable
    0.70
    CloseOperation
    0.69
     ―――――
    0.67
     дописавши
    0.67
    Activations Density 0.358%

    No Known Activations