© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1737
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or consensus in discussions

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

    Statements of agreement

    np_acts-logits-general · gemini-2.0-flash

    agreement with qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.81
    
    -0.71
     kasarigan
    -0.64
    verifyException
    -0.59
    emlrt
    -0.58
    initializeApp
    -0.52
    wpi
    -0.51
    δες
    -0.50
     Gewähr
    -0.48
     YellowPages
    -0.48
    POSITIVE LOGITS
     agree
    2.79
     agrees
    2.43
     Agree
    2.36
    Agree
    2.27
    agree
    2.26
     agreeing
    2.22
     agreed
    2.20
     disagree
    2.19
     Agreed
    2.09
    Agreed
    2.05
    Activations Density 0.375%

    No Known Activations