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. 402
    Prev
    Next
    INDEX
    Explanations

    nested structures in mathematical or programming contexts

    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
    ing
    -0.90
    ly
    -0.88
    C
    -0.81
    H
    -0.80
    h
    -0.78
    -
    -0.76
    𝐡
    -0.72
    quad
    -0.71
    T
    -0.69
    cl
    -0.69
    POSITIVE LOGITS
    ))),
    1.29
    )))
    1.29
    )}</
    1.26
    }}},
    1.26
    }}}
    1.17
    )]
    1.15
    ])]
    1.14
    )))))
    1.14
    ))}
    1.11
    setVerticalGroup
    1.11
    Activations Density 0.230%

    No Known Activations