© 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. 33-GEMMASCOPE-RES-16K
    6. 11057
    Prev
    Next
    INDEX
    Explanations

    medical terms and references in the context of healthcare and clinical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.66
    انجليز
    -0.55
    主义
    -0.46
     vermelhas
    -0.46
    المناصب
    -0.46
    hezza
    -0.46
    IsContent
    -0.45
     saveiro
    -0.45
    antiate
    -0.44
    zzati
    -0.44
    POSITIVE LOGITS
    Personensuche
    0.45
     onBind
    0.40
    OGND
    0.40
    <?
    0.39
    AnimationsModule
    0.39
    Ӕ
    0.39
     Med
    0.38
    coms
    0.37
    Xna
    0.37
    pack
    0.36
    Activations Density 0.569%

    No Known Activations