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. 25-GEMMASCOPE-RES-16K
    6. 1868
    Prev
    Next
    INDEX
    Explanations

    lists and structured data elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ."]
    -1.39
    ']);
    -1.26
    ”]
    -1.25
    ")]
    -1.23
    ']);
    
    -1.22
    "])
    -1.19
    </h6>
    -1.18
    ).]
    -1.17
    ")]
    
    -1.16
    ']
    
    -1.15
    POSITIVE LOGITS
    ]--;
    0.94
    ]<<"
    0.65
     propOrder
    0.62
    ]<<
    0.61
    ]>=
    0.59
    ]<=
    0.57
    Geplaatst
    0.56
     unknownFields
    0.56
    Géographie
    0.52
    ]=="
    0.51
    Activations Density 1.129%

    No Known Activations