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. 4736
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting related to citations and references

    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
    FACT
    -0.66
     Mann
    -0.65
    っか
    -0.65
    zhou
    -0.62
     bottom
    -0.61
     regular
    -0.60
     Morrison
    -0.59
     Maru
    -0.59
    brot
    -0.58
     bit
    -0.58
    POSITIVE LOGITS
    ()),
    1.47
    '),
    1.43
    ”),
    1.41
    "),
    1.40
    }),
    1.40
    )),
    1.40
    ]),
    1.39
    >),
    1.35
    ])),
    1.35
    ]),
    
    1.34
    Activations Density 0.465%

    No Known Activations