© 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. 31-GEMMASCOPE-RES-16K
    11. 9729
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities and experiences over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "has been" or similar perfect continuous constructions indicating past actions with present relevance.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cord
    -0.35
     later
    -0.33
     Later
    -0.31
    ūrė
    -0.30
    Later
    -0.30
     λογ
    -0.29
     hướng
    -0.29
     Wherever
    -0.29
     impar
    -0.28
     Fare
    -0.28
    POSITIVE LOGITS
     longtemps
    1.28
    一直
    1.25
     longstanding
    1.23
     давно
    1.21
     dlouho
    1.19
     longtime
    1.16
    我一直
    1.12
    一直在
    1.09
     długo
    1.09
     long
    1.09
    Activations Density 0.436%

    No Known Activations