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

    Neuronpedia

    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. 311
    Prev
    Next
    INDEX
    Explanations

    symbols and notation used in mathematical equations and formal proofs

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

    Mathematical or logical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code structures

    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
    geord
    -0.46
     Mr
    -0.45
    満
    -0.44
    gene
    -0.44
    сто
    -0.42
    /**
    -0.41
    Mr
    -0.41
     Lev
    -0.41
     le
    -0.40
     borer
    -0.40
    POSITIVE LOGITS
     فريبيس
    1.03
     $\
    0.92
    exitRule
    0.91
    fillType
    0.89
    adaptiveStyles
    0.86
    }{$\
    0.84
     Мексичка
    0.81
    ftagPool
    0.80
    ]),
    0.80
    principalColumn
    0.79
    Activations Density 1.790%

    No Known Activations