© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14002
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people, particularly "they" and "their."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
    INLINE
    -0.49
    <bos>
    -0.47
    isTrue
    -0.47
    providedIn
    -0.47
    strpos
    -0.44
    vin
    -0.44
     affari
    -0.43
     Circ
    -0.42
     Mar
    -0.41
     status
    -0.41
    POSITIVE LOGITS
    they
    1.18
     Mereka
    1.16
     mereka
    1.13
    Mereka
    1.13
     they
    1.12
    themselves
    1.11
    They
    1.11
     They
    1.09
     themselves
    1.08
    THEY
    1.04
    Activations Density 0.222%

    No Known Activations