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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 24
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and sequences

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

    Numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -1.05
    InputBorder
    -1.04
     AssemblyTitle
    -1.01
     ModelExpression
    -1.00
    :✨
    -1.00
     EconPapers
    -0.98
    ftagPool
    -0.86
    الإنجليزية
    -0.84
    AndEndTag
    -0.84
    曖昧さ回避
    -0.84
    POSITIVE LOGITS
    2
    0.69
    4
    0.64
    3
    0.63
    1
    0.56
    0
    0.56
    8
    0.55
    7
    0.54
     
    0.53
    5
    0.53
    9
    0.53
    Activations Density 0.209%

    No Known Activations