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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 3513
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands related to figure inclusion and formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.73
    insics
    -0.69
     '\\;'
    -0.69
    omeness
    -0.64
    toFloat
    -0.63
    netbeans
    -0.62
     referenties
    -0.61
    Geplaatst
    -0.61
    хьтан
    -0.61
     sanitaria
    -0.60
    POSITIVE LOGITS
    IBOutlet
    0.59
    Tembelea
    0.58
    Externí
    0.47
    اط
    0.45
    IBAction
    0.45
    ToFit
    0.45
     Obs
    0.44
     Савезне
    0.43
    XtraReports
    0.43
     للج
    0.43
    Activations Density 0.080%

    No Known Activations