© 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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10910
    Prev
    Next
    INDEX
    Explanations

    terms related to nighttime experiences and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.75
    }$​
    -0.73
    躇
    -0.73
    PhysRevD
    -0.72
    LookAnd
    -0.71
    Oggi
    -0.67
    brigens
    -0.64
     snapback
    -0.61
    AddWithValue
    -0.61
    phrag
    -0.61
    POSITIVE LOGITS
     night
    2.59
     nights
    2.36
     Night
    2.33
    Night
    2.30
     NIGHT
    2.29
    night
    2.21
     Nights
    2.15
    Nights
    2.12
    NIGHT
    2.04
    nights
    1.95
    Activations Density 0.043%

    No Known Activations