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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8645
    Prev
    Next
    INDEX
    Explanations

    quantifiers that indicate a high frequency or predominance in a group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referrerpolicy
    -0.38
    Бахар
    -0.37
    IZONT
    -0.37
     Bernardo
    -0.34
    žně
    -0.34
    reactstrap
    -0.33
     judgement
    -0.33
    antd
    -0.33
     Judgement
    -0.32
    ЙТЕ
    -0.32
    POSITIVE LOGITS
     itſelf
    0.63
     ſeveral
    0.56
    ſelf
    0.55
     invokingState
    0.51
     queſta
    0.50
     myſelf
    0.48
    ükemmel
    0.48
     ſch
    0.47
     quæ
    0.46
    verwijspagina
    0.46
    Activations Density 0.190%

    No Known Activations