© 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. 9915
    Prev
    Next
    INDEX
    Explanations

    terms related to financial products and their disclosures

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

    Followed by digits

    np_acts-logits-general · gemini-2.0-flash

    Magistrates Court

    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
    Colour
    -1.04
     programme
    -1.01
    initialise
    -1.01
     programmes
    -0.99
     centre
    -0.96
     utilise
    -0.95
    centred
    -0.95
    colour
    -0.94
     realises
    -0.94
    centre
    -0.92
    POSITIVE LOGITS
     snippetHide
    0.88
     theaters
    0.84
     كومونز
    0.79
    VersionUID
    0.79
    SharedDtor
    0.77
     Audiodateien
    0.76
     Majefty
    0.75
     Normdatei
    0.75
     nahilalakip
    0.73
     Houſe
    0.72
    Activations Density 0.057%

    No Known Activations