© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8427
    Prev
    Next
    INDEX
    Explanations

    terms related to iron availability and its effects on biological conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.67
    endpush
    -0.66
     lateinit
    -0.59
    MLLoader
    -0.57
    AnchorTagHelper
    -0.56
     BorderRadius
    -0.56
    MENAFN
    -0.56
    EDEFAULT
    -0.56
    astify
    -0.56
     članak
    -0.55
    POSITIVE LOGITS
     environment
    0.64
     conditions
    0.63
    での
    0.60
     condition
    0.59
     environments
    0.57
    条件
    0.56
    fiore
    0.56
     dAtA
    0.55
    环境
    0.53
    MigrationBuilder
    0.53
    Activations Density 1.220%

    No Known Activations