© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9986
    Prev
    Next
    INDEX
    Explanations

    statements indicating communication from authoritative sources or officials

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

    Someone "told" something to a news organization

    np_acts-logits-general · gemini-2.0-flash

    told to reporters

    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
     autorytatywna
    -0.54
    InitVars
    -0.49
     Italijani
    -0.48
     vicente
    -0.46
    cxx
    -0.45
     समीक्षाओं
    -0.45
    spender
    -0.44
     estekak
    -0.43
    SharedCtor
    -0.42
    LabelTagHelper
    -0.41
    POSITIVE LOGITS
     reporters
    0.81
     correspondents
    0.73
    tvguidetime
    0.66
     correspondent
    0.66
     reporter
    0.65
     News
    0.64
    __(/*!
    0.62
     reported
    0.62
    AndEndTag
    0.61
     repor
    0.61
    Activations Density 0.083%

    No Known Activations