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

    Neuronpedia

    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. 2027
    Prev
    Next
    INDEX
    Explanations

    instructions related to configuring settings in software

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

    Follows file/folder properties or settings

    np_acts-logits-general · gemini-2.0-flash

    navigating settings pages

    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
     Departmental
    -0.55
    ̍t
    -0.54
     departmental
    -0.51
    GenerationType
    -0.48
    <eos>
    -0.47
    DESK
    -0.45
    lillah
    -0.45
    djangoproject
    -0.43
    funeralhome
    -0.43
     ratification
    -0.42
    POSITIVE LOGITS
    tabPage
    0.68
    RenderAtEndOf
    0.66
     propOrder
    0.64
     tabs
    0.62
     tab
    0.60
     dAtA
    0.59
    general
    0.56
    enetic
    0.56
    overview
    0.55
    EditorGUILayout
    0.55
    Activations Density 0.153%

    No Known Activations