© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11265
    Prev
    Next
    INDEX
    Explanations

    syntax and structure elements of programming code

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

    Code block endings (often with "}")

    np_acts-logits-general · gemini-2.0-flash

    closing brace `}` or statement end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.71
    :✨
    -0.68
    Personendaten
    -0.59
    tagHelperRunner
    -0.57
     BorderSide
    -0.57
     surla
    -0.57
    Autoritní
    -0.57
    gonic
    -0.54
    AsUp
    -0.54
    $_['
    -0.54
    POSITIVE LOGITS
    didSet
    0.51
    enderror
    0.44
    ⎦
    0.40
    ']],
    0.40
    
    0.38
    esac
    0.37
    ┘
    0.36
    complexContent
    0.35
    )].
    0.34
     nhàng
    0.33
    Activations Density 0.098%

    No Known Activations