© 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. 7-GEMMASCOPE-RES-16K
    6. 14636
    Prev
    Next
    INDEX
    Explanations

    time zone information and monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.33
     compact
    -0.30
    曖昧さ回避
    -0.29
    AddTagHelper
    -0.28
     durar
    -0.28
    Ưu
    -0.26
     PARTY
    -0.26
    Недостатки
    -0.26
    makeConstraints
    -0.26
     pedigree
    -0.25
    POSITIVE LOGITS
    EDEFAULT
    0.64
    numerusform
    0.60
    rizona
    0.58
    ſſung
    0.54
    vespa
    0.54
     poffible
    0.53
    DIPSETTING
    0.52
    ロウィン
    0.52
    antism
    0.50
    UnsafeEnabled
    0.50
    Activations Density 0.295%

    No Known Activations