© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12797
    Prev
    Next
    INDEX
    Explanations

    transitional phrases that indicate a continuation or clarification of thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     also
    -0.81
     therefore
    -0.69
     finally
    -0.65
     sometimes
    -0.64
     actually
    -0.59
     témoig
    -0.59
     meanwhile
    -0.57
     now
    -0.57
     nevertheless
    -0.57
     simply
    -0.56
    POSITIVE LOGITS
     Certainly
    1.17
    Certainly
    1.14
    Ironically
    1.10
    Eventually
    1.09
     Eventually
    1.06
     Perhaps
    1.05
    Perhaps
    1.05
    Surely
    1.04
    Clearly
    1.04
    Personally
    1.04
    Activations Density 0.526%

    No Known Activations