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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 793
    Prev
    Next
    INDEX
    Explanations

    scholarly references or citations in scientific texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    years in academic citations and references.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    year values in citations (four-digit numbers typically found in parentheses within academic references).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $}}
    -0.72
     latter
    -0.57
    ]$}
    -0.55
    ]}>
    -0.52
    ()}}
    -0.51
    RenderAtEndOf
    -0.51
     }}$}
    -0.50
    "]}
    -0.49
    ()}>
    -0.49
    ']],
    -0.46
    POSITIVE LOGITS
    )
    1.13
    ),
    0.93
    )/
    0.90
    )-
    0.89
    ).
    0.79
    )'
    0.79
    )...
    0.77
    )+
    0.77
    )…
    0.76
    ):
    0.75
    Activations Density 2.706%

    No Known Activations