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. 12-GEMMASCOPE-RES-16K
    6. 1371
    Prev
    Next
    INDEX
    Explanations

    distinct pieces of punctuation and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FontWeight
    -0.68
    ércoles
    -0.61
    extAlignment
    -0.61
    ANCIAL
    -0.60
    gjenge
    -0.60
     
    -0.60
    khid
    -0.60
    URLEncoder
    -0.60
    ="<?=$
    -0.60
    fastjson
    -0.59
    POSITIVE LOGITS
    ])).
    1.34
    ))).
    1.33
    })).
    1.29
    )}.
    1.26
    }}.
    1.20
    }$.
    1.19
    }`).
    1.19
    $.}
    1.19
     }}$.
    1.18
    }.
    1.18
    Activations Density 2.419%

    No Known Activations