© 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. 20-GEMMASCOPE-RES-16K
    6. 12134
    Prev
    Next
    INDEX
    Explanations

    phrases related to scheduling and time management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.47
    
    -0.44
    migrationBuilder
    -0.43
    TypedDataSet
    -0.38
    ReusableCell
    -0.35
    MarshalTo
    -0.35
    ❷
    -0.35
    spender
    -0.35
    EndInit
    -0.34
     newOwner
    -0.34
    POSITIVE LOGITS
     daytime
    1.00
     afternoon
    0.96
     morning
    0.93
     evening
    0.90
     afternoons
    0.84
     night
    0.81
     daylight
    0.79
     mornings
    0.79
     nighttime
    0.77
     evenings
    0.75
    Activations Density 0.169%

    No Known Activations