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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 682
    Prev
    Next
    INDEX
    Explanations

    quantitative data points and their relationships in economic discussions

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

    academic citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.56
    XmlAccessType
    -0.55
    )]=
    -0.53
     Процитовано
    -0.53
    ]},
    -0.52
    })$}
    -0.52
     Aub
    -0.51
     }}$}
    -0.50
    Wik
    -0.50
    ])):
    -0.49
    POSITIVE LOGITS
     profesión
    0.53
    AndroidJUnit
    0.49
    bootstrapcdn
    0.49
     gouver
    0.49
    ResponseBody
    0.48
     gobier
    0.48
     Numerade
    0.47
     Савезне
    0.47
     votación
    0.47
     groupBox
    0.47
    Activations Density 0.012%

    No Known Activations