© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4011
    Prev
    Next
    INDEX
    Explanations

    repetitive references to the subject 'they' or 'them' in a context likely discussing characteristics or behaviors

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

    pronouns like "they", particularly when referring to technical or scientific concepts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    uxxxx
    -0.55
     ویکی‌آمباردا
    -0.54
    RegressionTest
    -0.51
     otomatig
    -0.50
    .*")]
    -0.46
    ']==
    -0.44
    ValueStyle
    -0.44
     initComponents
    -0.43
     <<<<<<<<<<<<<<
    -0.41
    routeProvider
    -0.39
    POSITIVE LOGITS
     meille
    0.50
     Italij
    0.48
    ähteet
    0.46
     oldukça
    0.45
     undoubtedly
    0.43
     todella
    0.43
     digna
    0.43
     contigo
    0.43
     Inscrivez
    0.43
    ſelves
    0.43
    Activations Density 0.278%

    No Known Activations