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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 1852
    Prev
    Next
    INDEX
    Explanations

    technical terms related to quantum mechanics and the properties of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onuc
    -0.49
    onucle
    -0.48
    BagConstraints
    -0.45
     STATEMENTS
    -0.44
    ERK
    -0.43
     Hou
    -0.43
    ulfate
    -0.43
    internalType
    -0.43
     statement
    -0.42
     stench
    -0.42
    POSITIVE LOGITS
    })`
    0.72
     виправивши
    0.71
     للاسماء
    0.68
    \{\\
    0.68
    Aholisi
    0.65
     bezeichneter
    0.65
     iſt
    0.60
     endforeach
    0.60
     AssemblyProduct
    0.60
     Hamlin
    0.60
    Activations Density 2.871%

    No Known Activations