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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 10442
    Prev
    Next
    INDEX
    Explanations

    programming constructs and methods related to data handling and user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktır
    -0.46
     congi
    -0.44
    IUrlHelper
    -0.43
     Erfurt
    -0.43
     calcite
    -0.42
     nød
    -0.41
     conjunta
    -0.41
     Jeu
    -0.41
    당
    -0.40
     Priory
    -0.40
    POSITIVE LOGITS
    ngOnInit
    1.46
    PreferredItem
    1.25
    Clik
    1.18
     consultato
    1.13
     onCreateView
    1.12
     doInBackground
    1.11
     onPostExecute
    1.10
     viewDidLoad
    1.10
    WebServlet
    1.07
     getItemCount
    1.05
    Activations Density 0.013%

    No Known Activations