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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9132
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time or duration

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

    expressions indicating a considerable passage of time, such as "it's been a long time" or "it's been years since."

    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
    WebElementEntity
    -0.65
    oa̍t
    -0.64
     gynhyrchwyd
    -0.55
     Савезне
    -0.50
    Chham
    -0.49
    씩
    -0.47
    Дереккөздер
    -0.44
    ContentAsync
    -0.43
    ichord
    -0.43
     ſche
    -0.43
    POSITIVE LOGITS
     since
    1.63
    since
    1.44
     depuis
    1.35
     sejak
    1.26
     SINCE
    1.25
     fince
    1.22
    Since
    1.21
     Since
    1.20
     desde
    1.16
     seit
    1.13
    Activations Density 0.292%

    No Known Activations