© 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. 31-GEMMASCOPE-RES-16K
    11. 8664
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the prefix "Ar" and its variations, indicating a focus on names or terms starting with "Ar."

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

    proper names beginning with "Ar" (like Arvida, Arthur, Arrabella, Arrests, Arror, Armage, Arber, Ardha).

    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
    }))
    -0.40
    ]]
    -0.39
    )|^{
    -0.35
    }}
    -0.33
    </table>
    -0.33
     }}}
    -0.33
    ')")
    -0.32
    )))
    -0.32
    ]))
    -0.32
    '},
    -0.32
    POSITIVE LOGITS
     يتيمه
    0.81
     Ar
    0.70
     AR
    0.69
    matchCondition
    0.68
    AnimationsModule
    0.62
    Ar
    0.61
    jsxFileName
    0.59
    ValueStyle
    0.59
    principalColumn
    0.59
     Aron
    0.56
    Activations Density 0.352%

    No Known Activations