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

    Neuronpedia

    APICircuit 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. 0-GEMMASCOPE-RES-16K
    6. 7817
    Prev
    Next
    INDEX
    Explanations

    block structures and programming constructs in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }})
    -1.17
    }}}}
    -1.15
    ])))
    -1.14
    }}}\
    -1.08
    )}}
    -1.08
    )))),
    -1.07
    }}},
    -1.06
    }])
    -1.05
    }}}
    -1.05
    }}}{
    -1.05
    POSITIVE LOGITS
    heça
    0.54
     such
    0.51
     of
    0.50
     ever
    0.47
    InjectMocks
    0.46
     Le
    0.46
     Bad
    0.45
     le
    0.42
    SetTitle
    0.42
     сезоне
    0.42
    Activations Density 0.398%

    No Known Activations