© 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. 18-GEMMASCOPE-RES-16K
    6. 11133
    Prev
    Next
    INDEX
    Explanations

    instances of data manipulation and retrieval in programming contexts

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

    Followed by names, emails, ids, code, or db

    np_acts-logits-general · gemini-2.0-flash

    object properties like name and id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    -0.68
     has
    -0.60
     size
    -0.59
     tỉ
    -0.56
     St
    -0.51
      
    -0.50
    '][]
    -0.50
     do
    -0.49
     these
    -0.48
     was
    -0.48
    POSITIVE LOGITS
     Jefus
    1.06
     Monfieur
    1.05
     themſelves
    1.00
     myſelf
    0.96
     Majefty
    0.95
     himſelf
    0.93
     Chriftian
    0.89
     Houſe
    0.86
     houſe
    0.82
     Efq
    0.81
    Activations Density 0.175%

    No Known Activations