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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73620
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    }}">
    -0.50
    }}}
    -0.48
     }}}
    -0.47
    }}}}
    -0.46
    ')))
    -0.45
    ISupport
    -0.44
    ())))
    -0.43
     }}">
    -0.43
    ("
    -0.43
    ]})
    -0.42
    POSITIVE LOGITS
    [...,
    0.61
    _{[
    0.61
    [:,
    0.57
    ViewChild
    0.54
     intStringLen
    0.53
    oliber
    0.52
    illaries
    0.52
     (_,
    0.51
     onBind
    0.50
    _{
    0.50
    Activations Density 0.066%

    No Known Activations