© 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. 16-GEMMASCOPE-RES-16K
    11. 7250
    Prev
    Next
    INDEX
    Explanations

    terms related to corporate structures and relationships

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

    a follow-up or related item

    np_acts-logits-general · gemini-2.0-flash

    successor, sequel, derivative, subsidiary, companion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下载附件
    -0.83
    zzleHttp
    -0.70
     AppModule
    -0.56
     đốc
    -0.53
     cellpadding
    -0.52
    ValueStyle
    -0.51
    motors
    -0.50
     Des
    -0.50
    mobileqq
    -0.49
    ölker
    -0.48
    POSITIVE LOGITS
     فريبيس
    1.08
     thereof
    0.75
     thereto
    0.70
     therefrom
    0.69
    󠁴
    0.65
     hereof
    0.60
     directos
    0.59
     femininas
    0.58
     nying
    0.58
    AutoScaleMode
    0.57
    Activations Density 0.753%

    No Known Activations