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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 7211
    Prev
    Next
    INDEX
    Explanations

    method calls related to displaying messages and constructing graphical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.70
    FromArgb
    -0.63
     ComVisible
    -0.59
    новништво
    -0.59
    @[+][
    -0.53
    DebuggerNonUser
    -0.52
    thebibliography
    -0.47
    释
    -0.45
     combatt
    -0.44
     Pulver
    -0.43
    POSITIVE LOGITS
     OnInit
    2.86
    makeText
    2.27
    AddTagHelper
    1.19
    ViewInit
    0.99
    AddHtmlAttribute
    0.94
     MatDialog
    0.86
    OnInit
    0.83
     createState
    0.83
    providedIn
    0.83
     jsPsych
    0.82
    Activations Density 0.037%

    No Known Activations