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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13099
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and coding questions, particularly focusing on PHP and its functionality

    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
    tvguidetime
    -0.66
     klink
    -0.54
    octanol
    -0.53
    PullParser
    -0.50
     وتسجيلات
    -0.50
    migrationBuilder
    -0.49
     xoay
    -0.48
    اعمال
    -0.45
    isEmail
    -0.44
     iNdEx
    -0.44
    POSITIVE LOGITS
     Quora
    0.69
    Datuak
    0.68
    Indented
    0.66
     CURIAM
    0.63
    PYX
    0.62
    सन्दर्भ
    0.61
    Geplaatst
    0.61
    xchange
    0.58
    arithmic
    0.58
    odeficiency
    0.58
    Activations Density 0.879%

    No Known Activations