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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15967
    Prev
    Next
    INDEX
    Explanations

    references to music albums or singles and their artists

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    }))
    
    -0.44
    UnitTesting
    -0.40
     jasa
    -0.39
    }])
    -0.38
    })));
    -0.37
     verrez
    -0.37
    ])).
    -0.36
     }]
    -0.35
    })).
    -0.33
     }],
    -0.33
    POSITIVE LOGITS
    InjectAttribute
    0.65
     الرياضيه
    0.56
     collabor
    0.53
    parsedMessage
    0.52
    mitz
    0.51
     collab
    0.51
     Collabor
    0.50
     Dear
    0.49
     partners
    0.47
     externi
    0.47
    Activations Density 0.033%

    No Known Activations