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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84632
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to gene expression and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.71
    Datuak
    -0.65
    IntoConstraints
    -0.60
    Clik
    -0.57
    twimg
    -0.54
    </u>
    -0.52
    </b>
    -0.52
    </strong>
    -0.51
     disponibilités
    -0.51
    Sucesor
    -0.48
    POSITIVE LOGITS
    }}}}
    0.41
    Manbalar
    0.37
    )))),
    0.36
     disambiguazione
    0.36
    enumii
    0.36
    \{\\
    0.36
    Carriera
    0.34
    Notae
    0.34
    }(),
    0.34
    }}},
    0.34
    Activations Density 0.406%

    No Known Activations