© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9146
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structural components in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ')))
    -0.49
     '))
    -0.48
    OCCURRED
    -0.46
    '))
    
    -0.45
    "]))
    -0.45
    ']))
    
    -0.42
     instead
    -0.42
    ')),
    -0.41
    adaptiveStyles
    -0.41
    '])
    
    -0.40
    POSITIVE LOGITS
    GEBURTS
    0.71
    Portail
    0.58
    awtextra
    0.54
     nakalista
    0.51
     يتيمه
    0.51
    Aholisi
    0.50
    tableFuture
    0.44
    bitat
    0.44
    Portale
    0.43
    NameInMap
    0.43
    Activations Density 0.893%

    No Known Activations