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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 696
    Prev
    Next
    INDEX
    Explanations

    phrases that express conditions, qualifications, or contrasts

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

    Followed by "said", "say" or "saying"

    np_acts-logits-general · gemini-2.0-flash

    says or said

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.53
    StoryboardSegue
    -0.48
     censiti
    -0.41
     toán
    -0.41
    intă
    -0.39
    führ
    -0.36
     cộng
    -0.36
    entlich
    -0.35
     kullanılır
    -0.34
     sisi
    -0.34
    POSITIVE LOGITS
     said
    3.21
     say
    2.88
    said
    2.68
     saying
    2.67
     says
    2.65
    Said
    2.57
     Said
    2.55
    say
    2.44
     SAID
    2.40
    Say
    2.37
    Activations Density 0.634%

    No Known Activations