© 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. 8-GEMMASCOPE-RES-16K
    11. 4341
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "say" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ']")
    -0.83
     Staub
    -0.82
    "]}
    -0.72
    ']}
    -0.70
     Angeles
    -0.67
    ledem
    -0.66
    "]]
    -0.66
    وردار
    -0.65
    lotten
    -0.64
     Inter
    -0.64
    POSITIVE LOGITS
     SAY
    1.76
    SAY
    1.67
     say
    1.64
     Says
    1.63
     says
    1.62
     Say
    1.62
    Say
    1.60
    Says
    1.59
     Saying
    1.58
    say
    1.56
    Activations Density 0.082%

    No Known Activations