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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4348
    Prev
    Next
    INDEX
    Explanations

    references to "stone" and its various forms, including "limestone" and "rock."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maintained
    -0.41
    ITRE
    -0.40
    prav
    -0.40
    zonder
    -0.39
    ismos
    -0.39
    ˵
    -0.38
    ญิง
    -0.38
    注
    -0.37
     combinação
    -0.37
    MODULE
    -0.37
    POSITIVE LOGITS
     BoxFit
    0.58
    yarnpkg
    0.51
    IVEREF
    0.50
    wall
    0.48
     mason
    0.47
    henge
    0.47
     []:
    0.44
    HMIS
    0.44
    walled
    0.44
    Geplaatst
    0.42
    Activations Density 0.182%

    No Known Activations