© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2967
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual or emotional support and resilience

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

    expressions of hope and support through imagery and reassurance

    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
    demos
    -0.40
    riez
    -0.38
    勿
    -0.38
    ỡng
    -0.38
     croire
    -0.37
     tom
    -0.37
    ACADEM
    -0.36
    werk
    -0.36
    َّ
    -0.35
    集合
    -0.35
    POSITIVE LOGITS
     Administrativna
    0.91
    MigrationBuilder
    0.88
     propOrder
    0.87
    kháu
    0.77
    WithIOException
    0.77
    цездатний
    0.75
    RegressionTest
    0.74
    CPtr
    0.74
    delwed
    0.73
    AddTagHelper
    0.73
    Activations Density 0.021%

    No Known Activations