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. 10000
    Prev
    Next
    INDEX
    Explanations

    code structures and function calls associated with data processing or manipulation

    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
     GenerationType
    -0.63
     efficiencies
    -0.55
    detectChanges
    -0.53
     betweenstory
    -0.52
    řev
    -0.52
    randomUUID
    -0.52
     schemes
    -0.49
     panels
    -0.49
    afel
    -0.48
    Lob
    -0.47
    POSITIVE LOGITS
    }`).
    0.87
    "]').
    0.83
    =").
    0.82
     "").
    0.77
    __).
    0.77
    ")->
    0.77
    ']").
    0.76
     %>%
    0.75
    >().
    0.72
    енча
    0.72
    Activations Density 0.096%

    No Known Activations