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. 6130
    Prev
    Next
    INDEX
    Explanations

    forms of the word "and"

    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
    +#+#
    -0.91
    fjspx
    -0.90
    featureID
    -0.76
     дописавши
    -0.75
    oredCriteria
    -0.73
     ब्रेकडाउन
    -0.73
     MaterialApp
    -0.71
    Sucesor
    -0.68
     Roskov
    -0.67
     nahilalakip
    -0.64
    POSITIVE LOGITS
     
    0.76
    <bos>
    0.70
    The
    0.62
    "
    0.62
     are
    0.62
    </b>
    0.61
    ).
    0.61
    '
    0.61
    }}
    0.58
    )
    0.58
    Activations Density 0.275%

    No Known Activations