© 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. 19-GEMMASCOPE-RES-16K
    11. 1762
    Prev
    Next
    INDEX
    Explanations

    statements and expressions of communication, particularly those involving the verb "say."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.65
    évaluateur
    -0.63
     <<<<<<<<<<<<<<
    -0.60
    SequentialGroup
    -0.59
    AutoField
    -0.58
     Maren
    -0.58
    商品説明
    -0.57
     Reine
    -0.56
     onCreateView
    -0.56
    <tfoot>
    -0.55
    POSITIVE LOGITS
     goodbye
    1.16
     hello
    0.88
     nothing
    0.72
     SAY
    0.71
    er
    0.71
     Say
    0.70
    goodbye
    0.70
    SAY
    0.68
    Say
    0.66
     yes
    0.65
    Activations Density 0.101%

    No Known Activations