© 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. 21-GEMMASCOPE-RES-16K
    11. 2194
    Prev
    Next
    INDEX
    Explanations

    constructs related to coding and data structure definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.67
    KommentareTeilen
    -0.64
     ويكيميديا
    -0.62
     GetEnumerator
    -0.58
    XmlAccessType
    -0.58
     Савезне
    -0.57
     contextLoads
    -0.56
    enterOuterAlt
    -0.56
    InputTagHelper
    -0.55
     InputDecoration
    -0.55
    POSITIVE LOGITS
     timestamp
    1.19
     time
    1.09
    timestamp
    1.07
     timestamps
    1.05
     created
    1.05
     Date
    1.04
     date
    1.04
    ctime
    1.03
    time
    1.01
     Timestamp
    1.00
    Activations Density 0.186%

    No Known Activations