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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7153
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or measurements in scientific contexts

    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
    fulness
    -0.62
    bran
    -0.59
     apa
    -0.57
     Vertra
    -0.55
     Gran
    -0.54
    đồng
    -0.54
    ment
    -0.53
     gron
    -0.53
    ương
    -0.52
     الغ
    -0.52
    POSITIVE LOGITS
    //
    1.21
    >)
    1.21
     propOrder
    1.20
    ”)
    1.19
    ())
    1.18
    }))
    1.15
    ])
    1.15
    })
    1.13
    ))
    1.12
    ])]
    1.09
    Activations Density 0.112%

    No Known Activations