© 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. 11565
    Prev
    Next
    INDEX
    Explanations

    terms related to jury behavior and courtroom procedures

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

    something is "outside"

    np_acts-logits-general · gemini-2.0-flash

    external links

    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
    #+#
    -0.80
    raborty
    -0.41
    Defaults
    -0.41
    weds
    -0.41
    гій
    -0.38
    뀜
    -0.37
    ำ
    -0.36
    myra
    -0.36
     näh
    -0.36
    ong
    -0.35
    POSITIVE LOGITS
     outside
    3.18
     Outside
    2.91
    Outside
    2.84
    outside
    2.83
     OUTSIDE
    2.60
     external
    2.36
    OUTSIDE
    2.25
     exterior
    2.12
     External
    2.04
     externally
    1.98
    Activations Density 0.535%

    No Known Activations