© 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. 41-GEMMASCOPE-RES-16K
    6. 6848
    Prev
    Next
    INDEX
    Explanations

    instances of the word "They" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -0.48
    TagMode
    -0.47
     during
    -0.47
    OrNil
    -0.45
     its
    -0.45
     on
    -0.44
    ForRow
    -0.44
     itself
    -0.42
    validates
    -0.41
     незавершена
    -0.41
    POSITIVE LOGITS
     berdua
    0.83
     themselves
    0.74
     all
    0.65
    themselves
    0.65
     too
    0.64
     way
    0.61
     mismos
    0.61
    Mereka
    0.59
     flesta
    0.58
     say
    0.58
    Activations Density 0.142%

    No Known Activations