Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15645
    Prev
    Next
    INDEX
    Explanations

    references to cleanliness and maintenance practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.56
     متعلقه
    -0.54
     isometric
    -0.53
    PickerController
    -0.53
     exerc
    -0.51
    GraphicsUnit
    -0.51
    artifactId
    -0.50
    ModelAdmin
    -0.49
    parametrize
    -0.49
    öfe
    -0.48
    POSITIVE LOGITS
     Spuren
    0.79
     traces
    0.78
     Traces
    0.66
     marks
    0.65
     aftermath
    0.65
     footprint
    0.65
     footprints
    0.64
     debris
    0.62
     residue
    0.62
     residues
    0.60
    Activations Density 0.341%

    No Known Activations