© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8866
    Prev
    Next
    INDEX
    Explanations

    key terms related to user interface elements and form inputs

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

    Preceding "_" or a letter

    np_acts-logits-general · gemini-2.0-flash

    private policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.60
     propOrder
    -0.54
    
    -0.54
    ########.
    -0.53
    tagHelperRunner
    -0.50
    postIndex
    -0.50
    Jeografia
    -0.49
    /**
    -0.49
    oneofs
    -0.48
     ModelExpression
    -0.47
    POSITIVE LOGITS
    </
    0.46
    httphttps
    0.43
    LookAnd
    0.43
    دانشنامهٔ
    0.42
    发表于
    0.42
     Payment
    0.42
    usercontent
    0.41
    sizePolicy
    0.41
     pleaſure
    0.40
    Rujuakan
    0.40
    Activations Density 0.476%

    No Known Activations