© 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. 31-GEMMASCOPE-RES-16K
    6. 572
    Prev
    Next
    INDEX
    Explanations

    instances of personal experiences and daily routines

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

    moments of waking up in the morning and descriptions of morning activities.

    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
    Tonight
    -0.46
    今晚
    -0.46
     tonight
    -0.45
    RTDA
    -0.45
     serata
    -0.44
     Nights
    -0.40
     Abend
    -0.39
     Tonight
    -0.38
    SharedCtor
    -0.38
    คืน
    -0.37
    POSITIVE LOGITS
     morning
    2.19
     breakfast
    1.95
    Morning
    1.93
     Morning
    1.91
     mornings
    1.88
    morning
    1.87
     Breakfast
    1.76
     MORNING
    1.73
    Breakfast
    1.71
    breakfast
    1.68
    Activations Density 0.368%

    No Known Activations