© 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. 23-GEMMASCOPE-RES-16K
    11. 5522
    Prev
    Next
    INDEX
    Explanations

    various contractions and possessive forms relating to negation or personal connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.62
     desapar
    -0.55
    IBOutlet
    -0.52
    AndroidJUnit
    -0.52
    ReusableCell
    -0.50
     tryck
    -0.50
     banques
    -0.49
     verksamhet
    -0.49
    Чыганаклар
    -0.47
     utilizamos
    -0.47
    POSITIVE LOGITS
     diffusivity
    0.69
    PhysRevD
    0.69
     pituitary
    0.69
     ventri
    0.64
     deposed
    0.64
    dBm
    0.63
     nhiêu
    0.63
     anthropogenic
    0.63
     forceps
    0.63
     hyaluronic
    0.63
    Activations Density 0.167%

    No Known Activations