© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1783
    Prev
    Next
    INDEX
    Explanations

    elements related to citation and references in academic texts

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

    technical or scientific references and citations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -1.00
    UrlResolution
    -0.98
     AssemblyCulture
    -0.98
    AddTagHelper
    -0.89
     ModelExpression
    -0.88
    Autoritní
    -0.85
    Geplaatst
    -0.85
     CreateTagHelper
    -0.84
    complexContent
    -0.83
     MainAxisSize
    -0.81
    POSITIVE LOGITS
    #
    0.41
    【
    0.40
    <strong>
    0.40
    (
    0.37
    The
    0.36
    E
    0.36
    US
    0.36
    I
    0.35
     Hirst
    0.35
    @
    0.35
    Activations Density 0.170%

    No Known Activations