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. 12597
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations in a formal text

    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
    )
    -0.79
    -
    -0.79
    s
    -0.73
    [toxicity=0]
    -0.71
    _
    -0.71
    }
    -0.70
    "
    -0.70
     of
    -0.66
    ]
    -0.64
    之
    -0.63
    POSITIVE LOGITS
    ſelves
    1.20
    expandindo
    1.16
    BibitemShut
    1.16
     /\.(
    1.12
     raiſ
    1.11
     ſche
    1.09
    ſelf
    1.09
     myſelf
    1.09
     uſ
    1.08
    ✨:
    1.03
    Activations Density 0.432%

    No Known Activations