© 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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1365
    Prev
    Next
    INDEX
    Explanations

    operations and processes related to data manipulation and estimation

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

    before actions or transformations

    np_acts-logits-general · gemini-2.0-flash

    processing and transforming data

    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
     propOrder
    -0.62
    uxxxx
    -0.61
    Personendaten
    -0.59
    BeginContext
    -0.58
    الإنجليزية
    -0.56
    лтемелер
    -0.56
     برانيه
    -0.56
    Tikang
    -0.56
     esternos
    -0.54
    
    -0.54
    POSITIVE LOGITS
     existing
    0.42
     the
    0.35
     gewel
    0.35
    HasForeignKey
    0.34
    existing
    0.34
    BagLayout
    0.33
     certain
    0.32
    掉
    0.32
     ζω
    0.32
     all
    0.31
    Activations Density 0.861%

    No Known Activations