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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 5944
    Prev
    Next
    INDEX
    Explanations

    higher-dimensional mathematical objects and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical symbols followed by delimiters

    np_acts-logits-general · gemini-2.0-flash

    latex math delimiters like `}`, `)`, `]`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "));
    -0.70
     "),
    -0.67
    )}.
    -0.63
     ").
    -0.62
    abetes
    -0.60
    }}.
    -0.60
    }.
    
    -0.58
     }}
    -0.56
    .}}
    -0.54
    ();
    
    
    -0.53
    POSITIVE LOGITS
    }$
    1.36
    )$
    1.30
    ]$
    1.12
    }}$
    1.06
    $
    1.02
    })$
    1.00
    \}$
    0.99
    )}$
    0.94
    ))$
    0.90
    }]$
    0.89
    Activations Density 1.612%

    No Known Activations