© 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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8906
    Prev
    Next
    INDEX
    Explanations

    references to message components in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    まっている
    -0.56
    ="{{$
    -0.47
    il
    -0.45
     ver
    -0.45
    ern
    -0.43
    hiers
    -0.43
     posi
    -0.43
     Der
    -0.42
    Der
    -0.41
    yv
    -0.41
    POSITIVE LOGITS
    +#+#
    1.01
    elemField
    0.86
     neceff
    0.84
    WriteTagHelper
    0.84
     تانيه
    0.82
     fubject
    0.80
     wife
    0.78
     nélk
    0.77
     myſelf
    0.77
    الإنجليزية
    0.76
    Activations Density 0.101%

    No Known Activations