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. 12-GEMMASCOPE-RES-16K
    6. 14783
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and related symbols in mathematical or code expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tof
    -0.82
     Loth
    -0.78
     Pg
    -0.77
    ̯
    -0.76
     Ribs
    -0.73
    帖最后由
    -0.73
    ing
    -0.73
     Altos
    -0.73
     fact
    -0.72
     Dawes
    -0.71
    POSITIVE LOGITS
    ))
    1.23
    ]))
    1.02
    ()))
    0.96
    ]]
    0.96
    )),
    0.94
    ]],
    0.90
    ])
    0.89
    ]])
    0.88
     ))
    0.87
    __))
    0.87
    Activations Density 0.449%

    No Known Activations