© 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. 2-GEMMASCOPE-RES-16K
    11. 15481
    Prev
    Next
    INDEX
    Explanations

    instances of the word "align" and its variations, indicating a focus on alignment concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.88
    InjectAttribute
    -0.81
    esModule
    -0.73
    colgroup
    -0.72
    ngdoc
    -0.68
     Tull
    -0.66
     Exacts
    -0.65
    expandindo
    -0.65
     {?>
    -0.64
    tagext
    -0.63
    POSITIVE LOGITS
     alignment
    3.14
     align
    3.00
     Alignment
    2.88
     aligned
    2.80
     Align
    2.70
     aligning
    2.67
    alignment
    2.63
    Alignment
    2.60
     aligns
    2.56
     ALIGN
    2.55
    Activations Density 0.069%

    No Known Activations