Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 10164
    Prev
    Next
    INDEX
    Explanations

    content related to professional roles and responsibilities, particularly in healthcare and nursing contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.93
     FetchType
    -0.89
    extAlignment
    -0.85
     المعيارى
    -0.85
    LEncoder
    -0.83
    NUMX
    -0.82
    ſhip
    -0.81
     cellpadding
    -0.80
    mybatisplus
    -0.79
    ENEFITS
    -0.78
    POSITIVE LOGITS
    .
    1.46
    ).
    1.29
    }$.
    1.28
    ))).
    1.25
    }.
    1.23
    $.
    1.23
    ].
    1.22
    。
    1.22
    ।
    1.20
    })).
    1.14
    Activations Density 2.470%

    No Known Activations