© 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. 9007
    Prev
    Next
    INDEX
    Explanations

    questions and speculations related to future outcomes or consequences

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

    following "what" or "happens"

    np_acts-logits-general · gemini-2.0-flash

    what happens if or when

    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
    WithIOException
    -0.77
    parsedMessage
    -0.74
     بيها
    -0.74
    __':
    -0.68
    styleType
    -0.62
    makeConstraints
    -0.58
    IntoConstraints
    -0.57
    SharedCtor
    -0.57
    offen
    -0.57
    kuuta
    -0.57
    POSITIVE LOGITS
     happens
    1.48
     Happens
    1.26
     happen
    1.22
    happens
    1.16
     when
    1.01
     occurs
    0.97
     acontece
    0.96
     result
    0.96
    happen
    0.91
     happened
    0.90
    Activations Density 0.291%

    No Known Activations