© 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. 18-GEMMASCOPE-RES-16K
    11. 10910
    Prev
    Next
    INDEX
    Explanations

    mentions of data management and planning strategies

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

    Follows noun phrases

    np_acts-logits-general · gemini-2.0-flash

    suffered from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]='\
    -0.61
     neighbouring
    -0.60
    ']='
    -0.56
     unfavourable
    -0.54
     voilà
    -0.54
     prerequisite
    -0.51
     jā
    -0.51
     strategic
    -0.50
    "]="
    -0.50
     interdependent
    -0.50
    POSITIVE LOGITS
     things
    0.77
     IBOutlet
    0.73
     المعيارى
    0.73
     useParams
    0.67
    Things
    0.66
     cosas
    0.65
     Things
    0.64
     dingen
    0.64
    BeginContext
    0.63
    Really
    0.62
    Activations Density 0.196%

    No Known Activations