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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 14602
    Prev
    Next
    INDEX
    Explanations

    specific names and terms associated with notable individuals and literary works

    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
     IGF
    -0.78
     Ire
    -0.73
     IU
    -0.70
     Ich
    -0.70
    IGF
    -0.69
    Économie
    -0.67
     IBC
    -0.67
    ihnachten
    -0.66
     incor
    -0.66
    frastructure
    -0.66
    POSITIVE LOGITS
    pyplot
    0.81
     blades
    0.72
     Fib
    0.69
     chop
    0.66
    exitRule
    0.64
    ControllerAdvice
    0.64
    Fib
    0.63
     comunit
    0.63
    haft
    0.63
     Chop
    0.63
    Activations Density 1.423%

    No Known Activations