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. 24-GEMMASCOPE-RES-16K
    6. 2244
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to functions and algebra

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

    Mathematical notation with symbols and indices

    np_acts-logits-general · gemini-2.0-flash

    mathematical variable definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    `),
    -1.08
    ])
    -1.00
    ]),
    -0.97
    ]);
    -0.96
    ]).
    -0.90
    >)
    -0.88
    })$
    -0.88
    })$,
    -0.86
    ])
    
    -0.86
    ].)
    -0.84
    POSITIVE LOGITS
     للمعارف
    0.58
    商品説明
    0.54
    ArgsConstructor
    0.51
     GetEnumerator
    0.49
    ClientRect
    0.47
     Justicia
    0.45
    featureID
    0.43
     Stateless
    0.43
     chng
    0.42
    🇶
    0.41
    Activations Density 0.760%

    No Known Activations