© 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. 6-GEMMASCOPE-RES-16K
    11. 3421
    Prev
    Next
    INDEX
    Explanations

    citations and references within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étoit
    -0.81
     AssemblyCompany
    -0.78
    følgelig
    -0.74
    ]")]
    -0.73
    __':
    -0.73
    CloseOperation
    -0.72
    ^(@)
    -0.72
    enumii
    -0.70
    ########.
    -0.70
     nargin
    -0.69
    POSITIVE LOGITS
     accessed
    0.51
     Viitattu
    0.47
    consulté
    0.46
    less
    0.46
    ,
    0.46
     viewed
    0.45
    anglicky
    0.45
    Slf
    0.45
    匠
    0.45
     cited
    0.44
    Activations Density 0.964%

    No Known Activations