© 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. 16-GEMMASCOPE-RES-16K
    11. 15234
    Prev
    Next
    INDEX
    Explanations

    terms related to account verification and recovery processes on social media platforms, particularly Facebook

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

    Strings from resource files with "com_accountkit"

    np_acts-logits-general · gemini-2.0-flash

    aplikacije i podatke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.93
    ,
    -0.71
    <eos>
    -0.65
     I
    -0.62
    /
    -0.61
    .
    -0.60
     o
    -0.59
     (
    -0.58
    =
    -0.56
    -
    -0.56
    POSITIVE LOGITS
     مشين
    1.15
    RenderAtEndOf
    1.08
     itſelf
    1.07
     photolibrary
    1.04
    ChildScrollView
    1.02
     ſind
    1.00
    ஦
    0.99
    <unused99>
    0.98
    <unused52>
    0.98
    <unused71>
    0.98
    Activations Density 0.042%

    No Known Activations