© 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. 13-GEMMASCOPE-RES-16K
    6. 6917
    Prev
    Next
    INDEX
    Explanations

    occurrences of 'NULL' in a programming context, particularly related to memory allocation and pointer manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.98
     Towne
    -0.86
     bross
    -0.86
    HasForeignKey
    -0.81
    fjspx
    -0.81
     follic
    -0.81
    Fow
    -0.81
    arraycopy
    -0.81
     BoxFit
    -0.81
     Aung
    -0.80
    POSITIVE LOGITS
     Sap
    0.82
     Carney
    0.81
    ə
    0.80
    Spe
    0.80
     Jep
    0.79
    ര്‍
    0.77
     Spe
    0.77
     sap
    0.76
     EUR
    0.74
     ​​
    0.73
    Activations Density 0.197%

    No Known Activations