© 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. 4-GEMMASCOPE-RES-16K
    11. 11786
    Prev
    Next
    INDEX
    Explanations

    terms related to rounding numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -1.07
     ModelExpression
    -1.01
     &___
    -0.95
    évaluateur
    -0.93
    ]--;
    -0.93
     Roskov
    -0.90
    EDEFAULT
    -0.88
     تانيه
    -0.85
    +#+#
    -0.85
    ATTN
    -0.84
    POSITIVE LOGITS
     round
    2.74
    round
    2.68
    Round
    2.57
     Round
    2.51
     ROUND
    2.48
    ROUND
    2.38
     rounds
    2.35
     Rounds
    2.06
    rounds
    1.94
    Rounds
    1.80
    Activations Density 0.039%

    No Known Activations