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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6387
    Prev
    Next
    INDEX
    Explanations

    mentions of "mantis" and its variants, indicating a focus on a specific subject or entity related to that term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }".
    -0.52
    躇
    -0.48
    }'.
    -0.48
    ']],
    -0.47
    }))
    -0.47
     })}
    -0.45
    '],'
    -0.45
    '])
    
    -0.44
    }),
    
    -0.44
    ]),
    
    -0.44
    POSITIVE LOGITS
     Rand
    0.76
     Dandy
    0.75
     Banner
    0.73
    anners
    0.73
    annotation
    0.73
    anson
    0.73
     Gant
    0.73
     Lancet
    0.71
     Hanson
    0.71
    Banner
    0.71
    Activations Density 1.104%

    No Known Activations