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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1375
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and acknowledgment of support

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

    "Without" or expressions of gratitude/reliance

    np_acts-logits-general · gemini-2.0-flash

    thanks, help, crucial, saved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.79
    rungsseite
    -0.72
     AssemblyTitle
    -0.71
    AutoScaleMode
    -0.71
     autorytatywna
    -0.66
    uxxxx
    -0.63
    <unused43>
    -0.61
    <unused47>
    -0.61
    <unused28>
    -0.61
    <unused8>
    -0.61
    POSITIVE LOGITS
     sayesinde
    0.64
     Thanks
    0.53
     thanks
    0.52
    のおかげ
    0.51
     saved
    0.50
     helped
    0.48
    Thanks
    0.48
    Díky
    0.48
     grâce
    0.48
     invaluable
    0.48
    Activations Density 0.304%

    No Known Activations