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. 4-GEMMASCOPE-RES-16K
    6. 15878
    Prev
    Next
    INDEX
    Explanations

    closing parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Goy
    -0.67
     Dol
    -0.65
    émon
    -0.65
    ushman
    -0.63
    tish
    -0.62
     Rosh
    -0.61
     trung
    -0.61
    ness
    -0.60
    ंध
    -0.59
    FORME
    -0.59
    POSITIVE LOGITS
    ])
    1.57
    }))
    1.52
    })
    1.51
    ))
    1.45
    ())
    1.45
    ]")]
    1.43
    )
    1.42
    '])
    1.41
    )])
    1.40
    )})
    1.39
    Activations Density 0.575%

    No Known Activations