Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 8997
    Prev
    Next
    INDEX
    Explanations

    blocks of code or programming structures represented by indentation or white space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.69
     Erle
    -0.63
    Headers
    -0.63
    Sze
    -0.63
    DebuggerNonUser
    -0.60
     Hardcore
    -0.60
     Prü
    -0.60
    ondy
    -0.60
    juk
    -0.59
     Couleur
    -0.59
    POSITIVE LOGITS
    ')")
    0.74
    ']")
    0.72
    ]})
    0.64
    ]-->
    0.60
    prehension
    0.59
    }')
    0.59
    ]))
    
    0.58
    ,))
    0.58
     })}
    0.57
    })}
    0.57
    Activations Density 0.087%

    No Known Activations