Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 6736
    Prev
    Next
    INDEX
    Explanations

    the word "actually" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <tr>
    -0.76
    hdashline
    -0.73
    zyści
    -0.71
     ILS
    -0.71
     BPS
    -0.70
     GenerationType
    -0.70
     DMS
    -0.70
     Kieran
    -0.70
     Brim
    -0.69
     CORS
    -0.69
    POSITIVE LOGITS
     actually
    1.60
    Actually
    1.44
    actually
    1.42
     Actually
    1.42
     ACTUALLY
    1.31
     actual
    1.19
    ACTUAL
    1.16
    Actual
    0.97
     Actual
    0.95
     ACTUAL
    0.93
    Activations Density 0.081%

    No Known Activations