© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4155
    Prev
    Next
    INDEX
    Explanations

    phrases relating to time references

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

    "at this" preceding time-related words

    np_acts-logits-general · gemini-2.0-flash

    present moment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.97
     newOwner
    -0.93
     '\\;'
    -0.89
     estekak
    -0.88
     betweenstory
    -0.87
     beginnetje
    -0.83
     GenerationType
    -0.81
     ModelExpression
    -0.77
    MigrationBuilder
    -0.77
    клопе
    -0.73
    POSITIVE LOGITS
     present
    2.07
     moment
    2.00
    present
    1.72
    moment
    1.55
     Present
    1.52
    Present
    1.49
     PRESENT
    1.47
     momento
    1.46
     Moment
    1.44
     présent
    1.38
    Activations Density 0.244%

    No Known Activations