Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4208
    Prev
    Next
    INDEX
    Explanations

    references to memory buffers in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.83
     صوتيه
    -0.63
     nakalista
    -0.62
     Jefus
    -0.59
     faſt
    -0.56
    Хьажоргаш
    -0.55
     demografica
    -0.54
     myſelf
    -0.54
    Concentr
    -0.54
     ***!
    -0.53
    POSITIVE LOGITS
    buffer
    0.90
     buffer
    0.84
    Buffer
    0.77
     buffers
    0.65
     Buffer
    0.64
     grace
    0.63
    buff
    0.54
    缓冲
    0.53
     buff
    0.51
     gym
    0.49
    Activations Density 0.138%

    No Known Activations