© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8800
    Prev
    Next
    INDEX
    Explanations

    references and specific notations commonly used in scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )))
    -1.24
    ])))
    -1.22
    ))),
    -1.20
    ))))
    -1.20
    ')))
    -1.18
    )))))
    -1.18
    )])
    -1.17
    ]))
    -1.16
    ())))
    -1.14
    )))),
    -1.13
    POSITIVE LOGITS
     distanciation
    0.52
    帖最后由
    0.51
     informée
    0.48
    Gweler
    0.46
     nakalista
    0.43
     المعيارى
    0.43
    Зноскі
    0.42
    Референце
    0.42
    BeginContext
    0.41
     Administrativna
    0.41
    Activations Density 2.882%

    No Known Activations