© 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. 14276
    Prev
    Next
    INDEX
    Explanations

    technical parameters related to computing devices and memory specifications

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

    RAM and memory specifications

    np_acts-logits-general · gemini-2.0-flash

    DDR DRAM memory controllers

    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
     facial
    -0.47
     Weeknd
    -0.47
    zao
    -0.47
    懈
    -0.45
    facial
    -0.45
    ContentAsync
    -0.45
    EndContext
    -0.44
    Wax
    -0.44
    вказ
    -0.44
    Webhook
    -0.43
    POSITIVE LOGITS
     memory
    1.02
     Memory
    0.94
    memory
    0.87
     RAM
    0.87
     MEMORY
    0.84
     DDR
    0.83
    Memory
    0.82
    RAM
    0.78
    ReusableCell
    0.77
     resourceCulture
    0.77
    Activations Density 0.343%

    No Known Activations