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-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 5164
    Prev
    Next
    INDEX
    Explanations

    structured data representations, particularly involving mathematical or programming expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.82
     nahilalakip
    -0.81
    yntaxException
    -0.80
    PerformLayout
    -0.80
    EndContext
    -0.79
    发表于
    -0.77
    findpost
    -0.75
     ComVisible
    -0.75
    BufferException
    -0.74
    principalColumn
    -0.74
    POSITIVE LOGITS
     lecteurs
    0.45
     policiers
    0.45
     katkıda
    0.44
     pyplot
    0.44
     ghép
    0.44
     archiv
    0.44
     vaults
    0.44
    اشی
    0.42
    блиоте
    0.42
     japon
    0.41
    Activations Density 2.175%

    No Known Activations