© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12617
    Prev
    Next
    INDEX
    Explanations

    punctuations and symbols shaping the structure of code

    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
    pretation
    -0.59
     betweenstory
    -0.55
     trung
    -0.54
     שוליים
    -0.53
    ("")]
    
    -0.53
    期刊论文
    -0.52
     ddelweddau
    -0.52
    Promotion
    -0.51
    ramide
    -0.51
    tily
    -0.51
    POSITIVE LOGITS
    uyasha
    0.73
    indd
    0.69
    __).
    0.68
    ])+
    0.68
    __*/
    0.68
     RegExp
    0.66
     giapp
    0.65
     IELTS
    0.65
     MediatR
    0.64
     sexuelle
    0.64
    Activations Density 0.106%

    No Known Activations