© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 6280
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to physical measurements and quantifiable variables

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

    Follows words like "to" and "the"

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by objects or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    
    -0.60
    RefNanny
    -0.57
    Portail
    -0.54
    __':
    
    -0.52
    hyrchwyd
    -0.47
    webElementXpaths
    -0.47
    ंदीखरीदारी
    -0.47
     hábiles
    -0.46
    évaluateur
    -0.45
    
    -0.45
    POSITIVE LOGITS
     surla
    0.42
    /**
    0.42
    openzeppelin
    0.41
     itemName
    0.40
    erapeutic
    0.39
    AddTagHelper
    0.38
    SEGUIR
    0.38
     manqué
    0.38
    cartão
    0.38
    ところです
    0.38
    Activations Density 9.300%

    No Known Activations