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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 15112
    Prev
    Next
    INDEX
    Explanations

    code elements and structures that indicate storage or data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.84
    "],
    -0.78
    '],
    -0.77
     ),
    -0.76
    "):
    -0.71
    '),
    -0.68
    tagext
    -0.68
    "},
    -0.67
     },
    -0.66
    "];
    -0.66
    POSITIVE LOGITS
    }
    0.93
    }
    0.55
    </tr>
    0.45
    )
    0.42
     Accesorios
    0.39
    EndGlobalSection
    0.39
     nocturno
    0.37
    țională
    0.36
    </thead>
    0.35
    })
    0.35
    Activations Density 0.113%

    No Known Activations