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. 16-GEMMASCOPE-RES-16K
    6. 1686
    Prev
    Next
    INDEX
    Explanations

    code structure and programming language syntax elements

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

    Lines containing "import" statements

    np_acts-logits-general · gemini-2.0-flash

    package and import statements

    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
    úsqueda
    -0.66
    WriteTagHelper
    -0.58
    ansible
    -0.57
    springframework
    -0.57
    rítica
    -0.56
    ientí
    -0.55
    Tetapi
    -0.55
    anke
    -0.53
     auffi
    -0.53
    ätta
    -0.53
    POSITIVE LOGITS
    ViewFeatures
    0.54
    XmlAccessType
    0.53
    Personendaten
    0.49
    /*
    0.49
     endowments
    0.49
     úteis
    0.48
    icitis
    0.47
    createClass
    0.47
    सन्दर्भ
    0.47
    忑
    0.46
    Activations Density 0.074%

    No Known Activations