© 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. 1-GEMMASCOPE-RES-16K
    6. 13163
    Prev
    Next
    INDEX
    Explanations

    references to data structures related to memory management, specifically stacks and heaps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebControls
    -0.78
     assolu
    -0.59
    csi
    -0.52
     Biro
    -0.51
    льевич
    -0.51
    المل
    -0.50
     IntPtr
    -0.50
     démar
    -0.49
    %;">
    -0.49
    hdashline
    -0.49
    POSITIVE LOGITS
     stack
    2.56
     stacks
    2.21
     Stack
    2.19
     STACK
    2.15
    stack
    2.04
    Stack
    1.98
    STACK
    1.96
     pile
    1.84
     Stacks
    1.75
    stacks
    1.74
    Activations Density 0.054%

    No Known Activations