© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11586
    Prev
    Next
    INDEX
    Explanations

    sequences of actions and events described in the narrative

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

    Followed by a step in a procedure

    np_acts-logits-general · gemini-2.0-flash

    then followed by actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hierbei
    -0.63
     inmiddels
    -0.61
     daher
    -0.58
     inzwischen
    -0.57
     '\\;'
    -0.56
     now
    -0.55
     pertanto
    -0.54
     mittlerweile
    -0.54
     wcześniej
    -0.53
     frattempo
    -0.52
    POSITIVE LOGITS
     proceeded
    0.67
     proceed
    0.59
    proceed
    0.54
     PROCEED
    0.52
     THEN
    0.51
     proceeding
    0.50
     proceeds
    0.47
     procede
    0.46
     Proceed
    0.46
     Далее
    0.45
    Activations Density 0.606%

    No Known Activations