© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1356
    Prev
    Next
    INDEX
    Explanations

    structured transitions and indications of sequence in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sih
    -0.51
    leyeb
    -0.46
     or
    -0.41
    этому
    -0.41
     számára
    -0.40
    lagos
    -0.40
     beberapa
    -0.40
     haar
    -0.39
     daardoor
    -0.39
    Παραπομπές
    -0.38
    POSITIVE LOGITS
     secondly
    1.46
    Secondly
    1.44
     Secondly
    1.44
     Thirdly
    1.25
     Lastly
    1.24
    Lastly
    1.23
    первых
    1.13
     Firstly
    1.11
    Firstly
    1.11
     lastly
    1.09
    Activations Density 0.204%

    No Known Activations