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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 5274
    Prev
    Next
    INDEX
    Explanations

    terms related to alignment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    hasMoreElements
    -0.43
    Gre
    -0.41
    Preferences
    -0.40
    cotch
    -0.40
     recours
    -0.40
     Gre
    -0.40
    jstor
    -0.39
    WEBPACK
    -0.39
    gdx
    -0.39
    Tikang
    -0.39
    POSITIVE LOGITS
     alignment
    1.94
     aligned
    1.87
     align
    1.86
     aligning
    1.77
     Align
    1.70
     Alignment
    1.70
     ALIGN
    1.66
     aligns
    1.65
     alignments
    1.59
    alignment
    1.52
    Activations Density 0.135%

    No Known Activations