© 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. 20-GEMMASCOPE-RES-16K
    6. 14663
    Prev
    Next
    INDEX
    Explanations

    components and decorators in Angular code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     protoimpl
    -0.58
     فريبيس
    -0.55
     defaultstate
    -0.54
    حياته
    -0.53
    CGRectMake
    -0.53
    ListItemIcon
    -0.53
    orianCalendar
    -0.51
    expandindo
    -0.51
    iſche
    -0.51
    +#+#
    -0.48
    POSITIVE LOGITS
    PreferredItem
    0.46
    styleable
    0.43
     PropTypes
    0.40
    StructEnd
    0.35
     propTypes
    0.32
    endcsname
    0.31
     owner
    0.31
    nagyobb
    0.30
    AttributeSet
    0.29
     pemilik
    0.29
    Activations Density 0.185%

    No Known Activations