© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10220
    Prev
    Next
    INDEX
    Explanations

    method definitions and lifecycle events in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sucesor
    -0.57
    geon
    -0.53
    quad
    -0.52
     CallOverrides
    -0.48
    bkz
    -0.46
    AGAIN
    -0.45
    <em>
    -0.44
     fronte
    -0.43
     &
    -0.43
    ↗
    -0.43
    POSITIVE LOGITS
     onCreate
    3.00
     onCreateView
    1.52
     viewDidLoad
    1.25
     OnInit
    1.19
    viewDidLoad
    1.05
     onPostExecute
    1.04
    IsPostBack
    0.99
     onResume
    0.96
    onViewCreated
    0.96
    ngOnInit
    0.94
    Activations Density 0.010%

    No Known Activations