© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11557
    Prev
    Next
    INDEX
    Explanations

    references to suitability and quality in product descriptions

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

    Code and non-English text

    np_acts-logits-general · gemini-2.0-flash

    idiopathic evaluation

    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
    ↵↵
    -0.68
    <eos>
    -0.67
      
    -0.62
     […]
    -0.58
    ↵
    -0.55
     ...
    -0.53
    ...
    -0.52
        
    -0.51
     }}">
    -0.51
     dem
    -0.50
    POSITIVE LOGITS
     мәкалә
    0.89
     Савезне
    0.78
    uxxxx
    0.76
     تانيه
    0.75
    Tikang
    0.74
     ujednoznacz
    0.73
    ponses
    0.70
     للمعارف
    0.69
    MigrationBuilder
    0.69
     useAuth
    0.68
    Activations Density 0.001%

    No Known Activations