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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-GEMMASCOPE-RES-16K
    6. 6291
    Prev
    Next
    INDEX
    Explanations

    escape characters and formatting symbols used in typesetting, particularly in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 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
     ExecuteAsync
    -0.82
    """.
    -0.70
    })$}
    -0.67
     }}$}
    -0.67
    HomeAsUpEnabled
    -0.67
     chauss
    -0.66
    })*/
    -0.64
     مشين
    -0.64
     gainera
    -0.64
     féd
    -0.64
    POSITIVE LOGITS
    \\
    1.49
    }\\
    1.47
    \\\\
    1.41
     "\\
    1.30
    ("\\
    1.29
    )\\
    1.25
     '\\
    1.23
    \\\
    1.22
     \\
    1.19
    "\\
    1.18
    Activations Density 0.469%

    No Known Activations