© 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. 18-GEMMASCOPE-RES-16K
    11. 3473
    Prev
    Next
    INDEX
    Explanations

    Java import statements related to libraries and packages

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

    Java-related code or imports

    np_acts-logits-general · gemini-2.0-flash

    java programming libraries

    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
     indipendente
    -0.67
    ConstraintMaker
    -0.66
    antaranya
    -0.65
     preghiera
    -0.65
     spesa
    -0.63
    +#+#
    -0.63
     fallu
    -0.63
     réglable
    -0.62
     préfé
    -0.62
     viață
    -0.59
    POSITIVE LOGITS
    PhysRev
    0.67
    OrNil
    0.65
     Privile
    0.54
    initState
    0.54
     Obec
    0.54
    Westfalen
    0.52
     Endor
    0.49
    validation
    0.49
     Kenny
    0.48
    useEffect
    0.48
    Activations Density 0.038%

    No Known Activations