© 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. 41-GEMMASCOPE-RES-16K
    11. 7483
    Prev
    Next
    INDEX
    Explanations

    references to mechanical components and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microbiome
    -0.65
     optimised
    -0.62
     behaviours
    -0.56
     gestão
    -0.53
     learnt
    -0.53
     scenarios
    -0.51
     optimisation
    -0.51
    ategorised
    -0.51
     woken
    -0.50
     Gestão
    -0.49
    POSITIVE LOGITS
     objectionable
    0.57
    ChildScrollView
    0.56
     Italijanski
    0.54
     satisfactorily
    0.52
     muß
    0.52
     appreciably
    0.51
     satisfactory
    0.51
    faßt
    0.51
     seldom
    0.50
     مشين
    0.49
    Activations Density 1.781%

    No Known Activations