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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13185
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to programming concepts and structures in code

    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
    ])+
    -0.59
    )}+
    -0.56
    }}+
    -0.55
    )}-\
    -0.54
    ))-
    -0.54
    ))+
    -0.53
    })+
    -0.52
    
    -0.51
    }}-
    -0.50
    )}+\
    -0.50
    POSITIVE LOGITS
     propOrder
    0.68
     يتيمه
    0.53
     Signalez
    0.50
     GenerationType
    0.50
     surla
    0.49
    FormTagHelper
    0.47
    copg
    0.47
    EDEFAULT
    0.47
    aryen
    0.46
    titleMargin
    0.46
    Activations Density 1.043%

    No Known Activations