© 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-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 4747
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty and frequency related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actually
    -1.23
     basically
    -1.18
     essentially
    -1.17
     realmente
    -1.16
     faktisk
    -1.13
    actually
    -1.12
     faktiskt
    -1.10
    essentially
    -1.07
     finalement
    -1.05
     simplesmente
    -1.05
    POSITIVE LOGITS
     speaking
    0.66
     hablando
    0.64
     parlant
    0.64
    ً
    0.60
     falando
    0.57
     parlando
    0.53
    speaking
    0.49
    ঃ
    0.48
    情况下
    0.48
    ٌ
    0.45
    Activations Density 0.873%

    No Known Activations