© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15534
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that express uncertainty or caution regarding future events

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

    Preceding qualifiers or intensifiers such as "too", "very", "only"

    np_acts-logits-general · gemini-2.0-flash

    too early

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.54
    Бахар
    -0.54
     Menon
    -0.54
     CreateTagHelper
    -0.51
     ongles
    -0.50
    Ikus
    -0.49
    escens
    -0.48
     laku
    -0.47
    └──
    -0.46
     filles
    -0.46
    POSITIVE LOGITS
     early
    1.75
    early
    1.53
    Early
    1.48
     Early
    1.45
     EARLY
    1.37
     preliminary
    1.18
    EARLY
    1.16
     premature
    1.11
     frühen
    1.07
    Preliminary
    0.99
    Activations Density 0.147%

    No Known Activations