© 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. 7-GEMMASCOPE-RES-16K
    11. 3178
    Prev
    Next
    INDEX
    Explanations

    segments indicating shifts or changes in context or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enterOuterAlt
    -0.66
    ClientSize
    -0.60
     Stamps
    -0.60
    новниш
    -0.59
    Phal
    -0.58
     assunto
    -0.58
    ñora
    -0.57
     StringTokenizer
    -0.55
     cæ
    -0.55
    DrawerLayout
    -0.55
    POSITIVE LOGITS
    の中には
    0.65
     CreateTagHelper
    0.64
    着一个
    0.53
    壤
    0.49
    }}">
    0.48
    :
    0.48
    满了
    0.47
     multiple
    0.47
    pejo
    0.47
     betweenstory
    0.46
    Activations Density 0.203%

    No Known Activations