© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10328
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "had" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Torrey
    -0.91
     perſon
    -0.89
     ſtate
    -0.88
     Reuter
    -0.86
     Erscheinung
    -0.85
     cauſe
    -0.84
     houſe
    -0.82
     perfons
    -0.81
    LLocation
    -0.80
     pleaſure
    -0.80
    POSITIVE LOGITS
     had
    2.48
     Had
    2.17
    Had
    2.10
    had
    2.02
     HAD
    1.96
     είχε
    1.46
     hatte
    1.44
    HAD
    1.43
     avait
    1.40
     hadden
    1.31
    Activations Density 0.092%

    No Known Activations